From fbf58aab0696eaa4f5b75f4cf5d63b0a6d6753a0 Mon Sep 17 00:00:00 2001
From: Alireza Kashani <alireza.kashanipour@gmail.com>
Date: Sun, 2 Apr 2023 23:22:26 +0200
Subject: [PATCH 01/24] added prompt for NER data generation

---
 guides/prompts-applications.md | 46 ++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/guides/prompts-applications.md b/guides/prompts-applications.md
index 21012f5..7ab66ad 100644
--- a/guides/prompts-applications.md
+++ b/guides/prompts-applications.md
@@ -55,6 +55,52 @@ A: Negative
 
 This is very useful. We use this example for a different test in another section of the guides.
 
+*Prompt:*
+```
+produce 3 wine reviews and label taste, flavor, aroma related token; present the result as a json file, in addition add the coordinate of each term for NER task
+```
+
+*Output:*
+```
+[
+  {
+    "review": "This Chardonnay has a rich, creamy texture with notes of vanilla and buttery oak. The taste is smooth and well-balanced, with a hint of tropical fruit on the finish.",
+    "tokens": [
+      {"text": "rich", "label": "flavor", "start": 5, "end": 9},
+      {"text": "creamy", "label": "texture", "start": 10, "end": 16},
+      {"text": "vanilla", "label": "flavor", "start": 28, "end": 35},
+      {"text": "buttery", "label": "flavor", "start": 40, "end": 47},
+      {"text": "oak", "label": "aroma", "start": 48, "end": 51},
+      {"text": "smooth", "label": "taste", "start": 61, "end": 67},
+      {"text": "well-balanced", "label": "taste", "start": 68, "end": 81},
+      {"text": "hint", "label": "flavor", "start": 89, "end": 93},
+      {"text": "tropical fruit", "label": "flavor", "start": 98, "end": 112},
+      {"text": "finish", "label": "taste", "start": 116, "end": 122}
+    ]
+  },
+  {
+    "review": "This Cabernet Sauvignon has a bold, full-bodied flavor with notes of black cherry and dark chocolate. The aroma is rich and complex, with hints of tobacco and leather.",
+    "tokens": [
+      {"text": "bold", "label": "flavor", "start": 5, "end": 9},
+      {"text": "full-bodied", "label": "texture", "start": 10, "end": 21},
+      {"text": "black cherry", "label": "flavor", "start": 30, "end": 42},
+      {"text": "dark chocolate", "label": "flavor", "start": 47, "end": 60},
+      {"text": "rich", "label": "aroma", "start": 69, "end": 73},
+      {"text": "complex", "label": "aroma", "start": 78, "end": 85},
+      {"text": "hints", "label": "aroma", "start": 90, "end": 96},
+      {"text": "tobacco", "label": "aroma", "start": 101, "end": 108},
+      {"text": "leather", "label": "aroma", "start": 113, "end": 120}
+    ]
+  },
+  {
+    "review": "This Riesling has a crisp, refreshing taste with notes of green apple and honey. The aroma is floral and fruity, with a hint of citrus.",
+    "tokens": [
+      {"text": "crisp", "label": "texture", "start": 5, "end": 10},
+      {"text": "refreshing", "label": "texture", "start": 12, "end": 22},
+      {"text": "green apple", "label": "flavor", "start": 31, "end": 42},
+    ]
+  }
+```
 ---
 
 ## PAL (Program-Aided Language Models)

From cb5b5e6c6daef3f69540f01229995a9bdc2d9bdf Mon Sep 17 00:00:00 2001
From: Elvis Saravia <ellfae@gmail.com>
Date: Mon, 3 Apr 2023 15:58:14 -0600
Subject: [PATCH 02/24] Update prompts-applications.md

---
 guides/prompts-applications.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/guides/prompts-applications.md b/guides/prompts-applications.md
index 7ab66ad..ae6706f 100644
--- a/guides/prompts-applications.md
+++ b/guides/prompts-applications.md
@@ -55,6 +55,8 @@ A: Negative
 
 This is very useful. We use this example for a different test in another section of the guides.
 
+Here is another prompt example showing how to leverage the LLM for data labeling/augmentation task.
+
 *Prompt:*
 ```
 produce 3 wine reviews and label taste, flavor, aroma related token; present the result as a json file, in addition add the coordinate of each term for NER task
@@ -217,4 +219,4 @@ More examples coming soon!
 
 [Previous Section (Advanced Prompting)](./prompts-advanced-usage.md)
 
-[Next Section (ChatGPT)](./prompts-chatgpt.md)
\ No newline at end of file
+[Next Section (ChatGPT)](./prompts-chatgpt.md)

From 3d599999f467166eafdb7e910356cae6030bbfb6 Mon Sep 17 00:00:00 2001
From: BeBraveBeCurious <42266336+BeBraveBeCurious@users.noreply.github.com>
Date: Tue, 4 Apr 2023 05:47:56 +0100
Subject: [PATCH 03/24] =?UTF-8?q?sister=20=E7=BF=BB=E8=AF=91=E4=B8=BA=20?=
 =?UTF-8?q?=E5=A6=B9=E5=A6=B9=E6=9B=B4=E5=90=88=E9=80=82?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

妹妹的年龄是我 6 岁时年龄的一半，而不是姐姐比我年龄还小
---
 pages/techniques/consistency.zh.mdx | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/pages/techniques/consistency.zh.mdx b/pages/techniques/consistency.zh.mdx
index 0de2807..be64c25 100644
--- a/pages/techniques/consistency.zh.mdx
+++ b/pages/techniques/consistency.zh.mdx
@@ -6,7 +6,7 @@
 
 *提示：*
 ```
-当我6岁时，我的姐姐是我的一半年龄。现在我70岁了，我的姐姐多大？
+当我6岁时，我的妹妹是我的一半年龄。现在我70岁了，我的妹妹多大？
 ```
 
 *输出：*
@@ -43,23 +43,23 @@ A：Michael最初有58个球。星期二他丢失了23个，所以在那之后
 Q：Olivia有23美元。她用每个3美元的价格买了五个百吉饼。她还剩多少钱？
 A：她用每个3美元的价格买了5个百吉饼。这意味着她花了5
 
-Q：当我6岁时，我的姐姐是我的一半年龄。现在我70岁了，我的姐姐多大？
+Q：当我6岁时，我的妹妹是我的一半年龄。现在我70岁了，我的妹妹多大？
 A：
 ```
 
 *输出1：*
 ```
-当我6岁时，我的姐姐是我的一半年龄，也就是3岁。现在我70岁了，所以她是70-3 = 67岁。答案是67。
+当我6岁时，我的妹妹是我的一半年龄，也就是3岁。现在我70岁了，所以她是70-3 = 67岁。答案是67。
 ```
 
 *输出2：*
 ```
-当叙述者6岁时，他的姐姐是他年龄的一半，也就是3岁。现在叙述者70岁了，他的姐姐应该是70-3 = 67岁。答案是67。
+当叙述者6岁时，他的妹妹是他年龄的一半，也就是3岁。现在叙述者70岁了，他的妹妹应该是70-3 = 67岁。答案是67。
 ```
 
 *输出3：*
 ```
-当我6岁时，我的姐姐是我的一半年龄，也就是3岁。现在我70岁了，所以她是70/2 = 35岁。答案是35。
+当我6岁时，我的妹妹是我的一半年龄，也就是3岁。现在我70岁了，所以她是70/2 = 35岁。答案是35。
 ```
 
-计算最终答案涉及几个步骤（详见论文），但为了简单起见，我们可以看到已经出现了大多数答案，因此这基本上将成为最终答案。
\ No newline at end of file
+计算最终答案涉及几个步骤（详见论文），但为了简单起见，我们可以看到已经出现了大多数答案，因此这基本上将成为最终答案。

From 8e33e5b7d51153f02d8931c6921e136262706ff4 Mon Sep 17 00:00:00 2001
From: Dan Marshall <danmar@microsoft.com>
Date: Tue, 4 Apr 2023 19:05:09 -0700
Subject: [PATCH 04/24] Update basics.en.mdx

Fix a small typo - give to given
---
 pages/introduction/basics.en.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/introduction/basics.en.mdx b/pages/introduction/basics.en.mdx
index 2892d45..ae50442 100644
--- a/pages/introduction/basics.en.mdx
+++ b/pages/introduction/basics.en.mdx
@@ -18,7 +18,7 @@ blue
 The sky is blue on a clear day. On a cloudy day, the sky may be gray or white.
 ```
 
-As you can see, the language model outputs a continuation of strings that make sense give the context `"The sky is"`. The output might be unexpected or far from the task we want to accomplish. 
+As you can see, the language model outputs a continuation of strings that make sense given the context `"The sky is"`. The output might be unexpected or far from the task we want to accomplish. 
 
 This basic example also highlights the necessity to provide more context or instructions on what specifically we want to achieve.
 
@@ -111,4 +111,4 @@ What a horrible show! //
 Negative
 ```
 
-Few-shot prompts enable in-context learning which is the ability of language models to learn tasks given a few demonstrations.
\ No newline at end of file
+Few-shot prompts enable in-context learning which is the ability of language models to learn tasks given a few demonstrations.

From 429ef52415cc726d11d0a817aa4a9d773a3f1498 Mon Sep 17 00:00:00 2001
From: komori556 <omori-tomohiro-sd@ynu.jp>
Date: Wed, 5 Apr 2023 20:20:09 +0900
Subject: [PATCH 05/24] add APE reference paper link

---
 pages/techniques/ape.en.mdx | 2 +-
 pages/techniques/ape.jp.mdx | 2 +-
 pages/techniques/ape.pt.mdx | 2 +-
 pages/techniques/ape.zh.mdx | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/pages/techniques/ape.en.mdx b/pages/techniques/ape.en.mdx
index 1a50cbb..dfe144f 100644
--- a/pages/techniques/ape.en.mdx
+++ b/pages/techniques/ape.en.mdx
@@ -12,7 +12,7 @@ Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
 
 The first step involves a large language model (as an inference model) that is given output demonstrations to generate instruction candidates for a task. These candidate solutions will guide the search procedure. The instructions are executed using a target model, and then the most appropriate instruction is selected based on computed evaluation scores. 
 
-APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt (Kojima et al., 2022).
+APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
 
 The prompt "Let's work this out it a step by step to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
 
diff --git a/pages/techniques/ape.jp.mdx b/pages/techniques/ape.jp.mdx
index dfafa9c..27b6cde 100644
--- a/pages/techniques/ape.jp.mdx
+++ b/pages/techniques/ape.jp.mdx
@@ -12,7 +12,7 @@ import APECOT from '../../img/ape-zero-shot-cot.png'
 
 最初のステップは、タスクのための指示候補を生成する推論モデルとしての大規模言語モデルを使用することです。これらの候補解は、検索手順を指導します。指示はターゲットモデルを使用して実行され、計算された評価スコアに基づいて最適な指示が選択されます。
 
-APEは、人間が設計した「一緒にステップバイステップで考えてみましょう」というプロンプトよりも優れたゼロショットCoTプロンプトを発見しました（Kojima et al.、2022）。
+APEは、人間が設計した「一緒にステップバイステップで考えてみましょう」というプロンプトよりも優れたゼロショットCoTプロンプトを発見しました（[Kojima et al.、2022](https://arxiv.org/abs/2205.11916)）。
 
 「一緒にステップバイステップで作業し、正しい答えを確認するために」のプロンプトは、思考の連鎖を引き起こし、MultiArithおよびGSM8Kベンチマークのパフォーマンスを向上させます。
 
diff --git a/pages/techniques/ape.pt.mdx b/pages/techniques/ape.pt.mdx
index fa9c1c1..2c75249 100644
--- a/pages/techniques/ape.pt.mdx
+++ b/pages/techniques/ape.pt.mdx
@@ -12,7 +12,7 @@ Fonte da imagem: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
 
 A primeira etapa envolve um grande modelo de linguagem (como um modelo de inferência) que recebe demonstrações de saída para gerar candidatos de instrução para uma tarefa. Essas soluções candidatas guiarão o procedimento de busca. As instruções são executadas usando um modelo de destino e, em seguida, a instrução mais apropriada é selecionada com base nas pontuações de avaliação computadas.
 
-O APE descobre um prompt de CoT zero-shot melhor do que o prompt "Vamos pensar passo a passo" projetado por humanos (Kojima et al., 2022).
+O APE descobre um prompt de CoT zero-shot melhor do que o prompt "Vamos pensar passo a passo" projetado por humanos ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
 
 O prompt "Vamos resolver isso passo a passo para ter certeza de que temos a resposta certa." provoca raciocínio em cadeia e melhora o desempenho nos benchmarks MultiArith e GSM8K:
 
diff --git a/pages/techniques/ape.zh.mdx b/pages/techniques/ape.zh.mdx
index c5ad2da..89b400c 100644
--- a/pages/techniques/ape.zh.mdx
+++ b/pages/techniques/ape.zh.mdx
@@ -12,7 +12,7 @@ import APECOT from '../../img/ape-zero-shot-cot.png'
 
 第一步涉及一个大型语言模型（作为推理模型），该模型接收输出演示以生成任务的指令候选项。这些候选解将指导搜索过程。使用目标模型执行指令，然后根据计算的评估分数选择最合适的指令。
 
-APE发现了一个比人工设计的“让我们一步一步地思考”提示更好的零样本CoT提示（Kojima等人，2022）。
+APE发现了一个比人工设计的“让我们一步一步地思考”提示更好的零样本CoT提示（[Kojima等人，2022](https://arxiv.org/abs/2205.11916)）。
 
 提示“让我们一步一步地解决这个问题，以确保我们有正确的答案。”引发了思维链的推理，并提高了MultiArith和GSM8K基准测试的性能：
 

From 209d79b354a1692d7754413c32eefac87bea0f93 Mon Sep 17 00:00:00 2001
From: Yash Sharma <yashsharma0906@gmail.com>
Date: Wed, 5 Apr 2023 08:38:07 -0400
Subject: [PATCH 06/24] Added another reading resource

---
 pages/readings.en.mdx | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/pages/readings.en.mdx b/pages/readings.en.mdx
index fc8b81e..63664f7 100644
--- a/pages/readings.en.mdx
+++ b/pages/readings.en.mdx
@@ -110,4 +110,5 @@
 - [Unlocking Creativity with Prompt Engineering](https://youtube.com/watch?v=PFsbWAC4_rk&feature=shares)
 - [Using GPT-Eliezer against ChatGPT Jailbreaking](https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking)
 - [What Is ChatGPT Doing … and Why Does It Work?](https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/)
-- [Why is ChatGPT so good?](https://scale.com/blog/chatgpt-reinforcement-learning)
\ No newline at end of file
+- [Why is ChatGPT so good?](https://scale.com/blog/chatgpt-reinforcement-learning)
+- [Anyone can Design! With a little help from Generative AI](https://github.com/YashSharma/PromptEngineering)

From ce0db84a9a821327a3d772e6566a5791055cba6c Mon Sep 17 00:00:00 2001
From: bclavie <ben.clavie@brightnetwork.co.uk>
Date: Wed, 5 Apr 2023 17:15:26 +0100
Subject: [PATCH 07/24] Adding grad job classification case study paper and
 summary

---
 pages/applications/_meta.en.json              |  7 ++-
 pages/applications/workplace_casestudy.en.mdx | 56 +++++++++++++++++++
 pages/papers.en.mdx                           |  3 +-
 3 files changed, 62 insertions(+), 4 deletions(-)
 create mode 100644 pages/applications/workplace_casestudy.en.mdx

diff --git a/pages/applications/_meta.en.json b/pages/applications/_meta.en.json
index e34b985..9d47030 100644
--- a/pages/applications/_meta.en.json
+++ b/pages/applications/_meta.en.json
@@ -1,4 +1,5 @@
 {
-    "pal": "Program-Aided Language Models",
-    "generating": "Generating Data"
-}
\ No newline at end of file
+  "pal": "Program-Aided Language Models",
+  "generating": "Generating Data",
+  "workplace_casestudy": "Graduate Job Classifcation Case Study"
+}
diff --git a/pages/applications/workplace_casestudy.en.mdx b/pages/applications/workplace_casestudy.en.mdx
new file mode 100644
index 0000000..8f75dcb
--- /dev/null
+++ b/pages/applications/workplace_casestudy.en.mdx
@@ -0,0 +1,56 @@
+# LLMs as Graduate Job Classifiers Case-Study
+
+[Clavié et al., 2023](https://arxiv.org/abs/2303.07142) provide a case-study on prompt-engineering applied to a medium-scale text classification use-case in a production system. Using the task of classifying whether a job is a true "entry-level job", suitable for a recent graduate, or not, they evaluated a series of prompt engineering techniques and report their results using GPT-3.5 (`gpt-3.5-turbo`).
+
+The work shows that LLMs outperforms all other models tested, including an extremely strong baseline in DeBERTa-V3. `gpt-3.5-turbo` also noticeably outperforms older GPT3 variants in all key metrics, but requires additional output parsing as its ability to stick to a template appears to be worse than the other variants.
+
+The key findings of their prompt engineering approach are:
+
+- For tasks such as this one, where no expert knowledge is required, Few-shot CoT prompting performed worse than Zero-shot prompting in all experiments.
+- The impact of the prompt on eliciting the correct reasoning is massive. Simply asking the model to classify a given job results in an F1 score of 65.6, whereas the post-prompt engineering model achieves an F1 score of 91.7.
+- Attempting to force the model to stick to a template lowers performance in all cases (this behaviour disappears in early testing with GPT-4, which are posterior to the paper).
+- Many small modifications have an outsized impact on performance.
+ - The tables below show the full modifications tested.
+ - Properly giving instructions and repeating the key points appears to be the biggest performance driver.
+ - Something as simple as giving the model a (human) name and referring to it as such increased F1 score by 0.6pts.
+
+### Prompt Modifications Tested
+
+| Short name | Description                                                                |
+|------------|----------------------------------------------------------------------------|
+| Baseline   | Provide a a job posting and asking if it is fit for a graduate.            |
+| CoT        | Give a few examples of accurate classification before querying.            |
+| Zero-CoT   | Ask the model to reason step-by-step before providing its answer.          |
+| rawinst    | Give instructions about its role and the task by adding to the user msg.   |
+| sysinst    | Give instructions about its role and the task as a system msg.             |
+| bothinst   | Split instructions with role as a system msg and task as a user msg.       |
+| mock       | Give task instructions by mocking a discussion where it acknowledges them. |
+| reit       | Reinforce key elements in the instructions by repeating them.              |
+| strict     | Ask the model to answer by strictly following a given template.            |
+| loose      | Ask for just the final answer to be given following a given template.      |
+| right      | Asking the model to reach the right conclusion.                            |
+| info       | Provide additional information to address common reasoning failures.       |
+| name       | Give the model a name by which we refer to it in conversation.             |
+| pos        | Provide the model with positive feedback before querying it.               |
+
+
+### Performance Impact of All Prompt Modifications
+
+|                                        | Precision     | Recall        | F1            | Template Stickiness    |
+|----------------------------------------|---------------|---------------|---------------|------------------------|
+| _Baseline_                             | _61.2_        | _70.6_        | _65.6_        | _79%_                  |
+| _CoT_                                  | _72.6_        | _85.1_        | _78.4_        | _87%_                  |
+| _Zero-CoT_                             | _75.5_        | _88.3_        | _81.4_        | _65%_                  |
+| _+rawinst_                             | _80_          | _92.4_        | _85.8_        | _68%_                  |
+| _+sysinst_                             | _77.7_        | _90.9_        | _83.8_        | _69%_                  |
+| _+bothinst_                            | _81.9_        | _93.9_        | _87.5_        | _71%_                  |
+| +bothinst+mock                         | 83.3          | 95.1          | 88.8          | 74%                    |
+| +bothinst+mock+reit                    | 83.8          | 95.5          | 89.3          | 75%                    |
+| _+bothinst+mock+reit+strict_           | _79.9_        | _93.7_        | _86.3_        | _**98%**_              |
+| _+bothinst+mock+reit+loose_            | _80.5_        | _94.8_        | _87.1_        | _95%_                  |
+| +bothinst+mock+reit+right              | 84            | 95.9          | 89.6          | 77%                    |
+| +bothinst+mock+reit+right+info         | 84.9          | 96.5          | 90.3          | 77%                    |
+| +bothinst+mock+reit+right+info+name    | 85.7          | 96.8          | 90.9          | 79%                    |
+| +bothinst+mock+reit+right+info+name+pos| **86.9**      | **97**        | **91.7**      | 81%                    |
+
+**Impact of the various prompt modifications.**
diff --git a/pages/papers.en.mdx b/pages/papers.en.mdx
index 18fc9ab..06fdb35 100644
--- a/pages/papers.en.mdx
+++ b/pages/papers.en.mdx
@@ -133,6 +133,7 @@ The following are the latest papers (sorted by release date) on prompt engineeri
   - [Large Language Models and Simple, Stupid Bugs](https://arxiv.org/abs/2303.11455) (March 2023)
   - [Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?](https://arxiv.org/abs/2303.09325) (Mar 2023)
   - [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://arxiv.org/abs/2303.08896) (Mar 2023)
+  - [Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification](https://arxiv.org/abs/2303.07142) (March 2023)
   - [ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction](https://arxiv.org/abs/2303.05063) (March 2023)
   - [MathPrompter: Mathematical Reasoning using Large Language Models](https://arxiv.org/abs/2303.05398) (March 2023)
   - [Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forums](https://arxiv.org/abs/2303.05400) (March 2023)
@@ -170,4 +171,4 @@ The following are the latest papers (sorted by release date) on prompt engineeri
 
   - [Chain-of-Thought Papers](https://github.com/Timothyxxx/Chain-of-ThoughtsPapers)
   - [Papers with Code](https://paperswithcode.com/task/prompt-engineering)
-  - [Prompt Papers](https://github.com/thunlp/PromptPapers#papers)
\ No newline at end of file
+  - [Prompt Papers](https://github.com/thunlp/PromptPapers#papers)

From d0c329f71c29f227ed0c1a78618a66d22bcc6000 Mon Sep 17 00:00:00 2001
From: bclavie <ben.clavie@brightnetwork.co.uk>
Date: Wed, 5 Apr 2023 17:17:14 +0100
Subject: [PATCH 08/24] list indent

---
 pages/applications/workplace_casestudy.en.mdx | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/pages/applications/workplace_casestudy.en.mdx b/pages/applications/workplace_casestudy.en.mdx
index 8f75dcb..c0012e1 100644
--- a/pages/applications/workplace_casestudy.en.mdx
+++ b/pages/applications/workplace_casestudy.en.mdx
@@ -10,9 +10,9 @@ The key findings of their prompt engineering approach are:
 - The impact of the prompt on eliciting the correct reasoning is massive. Simply asking the model to classify a given job results in an F1 score of 65.6, whereas the post-prompt engineering model achieves an F1 score of 91.7.
 - Attempting to force the model to stick to a template lowers performance in all cases (this behaviour disappears in early testing with GPT-4, which are posterior to the paper).
 - Many small modifications have an outsized impact on performance.
- - The tables below show the full modifications tested.
- - Properly giving instructions and repeating the key points appears to be the biggest performance driver.
- - Something as simple as giving the model a (human) name and referring to it as such increased F1 score by 0.6pts.
+  - The tables below show the full modifications tested.
+  - Properly giving instructions and repeating the key points appears to be the biggest performance driver.
+  - Something as simple as giving the model a (human) name and referring to it as such increased F1 score by 0.6pts.
 
 ### Prompt Modifications Tested
 
@@ -53,4 +53,4 @@ The key findings of their prompt engineering approach are:
 | +bothinst+mock+reit+right+info+name    | 85.7          | 96.8          | 90.9          | 79%                    |
 | +bothinst+mock+reit+right+info+name+pos| **86.9**      | **97**        | **91.7**      | 81%                    |
 
-**Impact of the various prompt modifications.**
+Template stickiness refers to how frequently the model answers in the desired format. 

From 97eb672e3cbde52972235817ed78706f19edb018 Mon Sep 17 00:00:00 2001
From: bclavie <ben.clavie@brightnetwork.co.uk>
Date: Wed, 5 Apr 2023 17:25:58 +0100
Subject: [PATCH 09/24] json formatting + title matching

---
 pages/applications/_meta.en.json              | 6 +++---
 pages/applications/workplace_casestudy.en.mdx | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/pages/applications/_meta.en.json b/pages/applications/_meta.en.json
index 9d47030..8c23b98 100644
--- a/pages/applications/_meta.en.json
+++ b/pages/applications/_meta.en.json
@@ -1,5 +1,5 @@
 {
-  "pal": "Program-Aided Language Models",
-  "generating": "Generating Data",
-  "workplace_casestudy": "Graduate Job Classifcation Case Study"
+    "pal": "Program-Aided Language Models",
+    "generating": "Generating Data",
+    "workplace_casestudy": "Graduate Job Classification Case Study"
 }
diff --git a/pages/applications/workplace_casestudy.en.mdx b/pages/applications/workplace_casestudy.en.mdx
index c0012e1..d5297af 100644
--- a/pages/applications/workplace_casestudy.en.mdx
+++ b/pages/applications/workplace_casestudy.en.mdx
@@ -1,4 +1,4 @@
-# LLMs as Graduate Job Classifiers Case-Study
+# Graduate Job Classification Case Study
 
 [Clavié et al., 2023](https://arxiv.org/abs/2303.07142) provide a case-study on prompt-engineering applied to a medium-scale text classification use-case in a production system. Using the task of classifying whether a job is a true "entry-level job", suitable for a recent graduate, or not, they evaluated a series of prompt engineering techniques and report their results using GPT-3.5 (`gpt-3.5-turbo`).
 

From aebd1b1c11af5a2e1152b1a95a36efce702db4ba Mon Sep 17 00:00:00 2001
From: Elvis Saravia <ellfae@gmail.com>
Date: Wed, 5 Apr 2023 16:36:19 -0600
Subject: [PATCH 10/24] Update readings.en.mdx

---
 pages/readings.en.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/readings.en.mdx b/pages/readings.en.mdx
index 63664f7..53f6e13 100644
--- a/pages/readings.en.mdx
+++ b/pages/readings.en.mdx
@@ -2,12 +2,12 @@
 #### (Sorted by Name)
 
 - [2023 AI Index Report](https://aiindex.stanford.edu/report/)
-- [【徹底解説】これからのエンジニアの必携スキル、プロンプトエンジニアリングの手引「Prompt Engineering Guide」を読んでまとめてみた](https://dev.classmethod.jp/articles/how-to-design-prompt-engineering/)
 - [3 Principles for prompt engineering with GPT-3](https://www.linkedin.com/pulse/3-principles-prompt-engineering-gpt-3-ben-whately)
 - [A beginner-friendly guide to generative language models - LaMBDA guide](https://aitestkitchen.withgoogle.com/how-lamda-works)
 - [A Complete Introduction to Prompt Engineering for Large Language Models](https://www.mihaileric.com/posts/a-complete-introduction-to-prompt-engineering)
 - [A Generic Framework for ChatGPT Prompt Engineering](https://medium.com/@thorbjoern.heise/a-generic-framework-for-chatgpt-prompt-engineering-7097f6513a0b)
 - [An SEO’s guide to ChatGPT prompts](https://searchengineland.com/chatgpt-prompts-seo-393523)
+- [Anyone can Design! With a little help from Generative AI](https://github.com/YashSharma/PromptEngineering)
 - [AI Content Generation](https://www.jonstokes.com/p/ai-content-generation-part-1-machine)
 - [AI's rise generates new job title: Prompt engineer](https://www.axios.com/2023/02/22/chatgpt-prompt-engineers-ai-job)
 - [AI Safety, RLHF, and Self-Supervision - Jared Kaplan | Stanford MLSys #79](https://www.youtube.com/watch?v=fqC3D-zNJUM&ab_channel=StanfordMLSysSeminars)
@@ -111,4 +111,4 @@
 - [Using GPT-Eliezer against ChatGPT Jailbreaking](https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking)
 - [What Is ChatGPT Doing … and Why Does It Work?](https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/)
 - [Why is ChatGPT so good?](https://scale.com/blog/chatgpt-reinforcement-learning)
-- [Anyone can Design! With a little help from Generative AI](https://github.com/YashSharma/PromptEngineering)
+- [【徹底解説】これからのエンジニアの必携スキル、プロンプトエンジニアリングの手引「Prompt Engineering Guide」を読んでまとめてみた](https://dev.classmethod.jp/articles/how-to-design-prompt-engineering/)

From 80e8ca8788a3e191a0c223a09f44c1f2e85121b1 Mon Sep 17 00:00:00 2001
From: Elvis Saravia <ellfae@gmail.com>
Date: Wed, 5 Apr 2023 17:30:46 -0600
Subject: [PATCH 11/24] added case study

---
 pages/applications/_meta.jp.json              | 3 ++-
 pages/applications/_meta.pt.json              | 3 ++-
 pages/applications/_meta.zh.json              | 3 ++-
 pages/applications/workplace_casestudy.jp.mdx | 3 +++
 pages/applications/workplace_casestudy.pt.mdx | 3 +++
 pages/applications/workplace_casestudy.zh.mdx | 3 +++
 6 files changed, 15 insertions(+), 3 deletions(-)
 create mode 100644 pages/applications/workplace_casestudy.jp.mdx
 create mode 100644 pages/applications/workplace_casestudy.pt.mdx
 create mode 100644 pages/applications/workplace_casestudy.zh.mdx

diff --git a/pages/applications/_meta.jp.json b/pages/applications/_meta.jp.json
index f450929..dc236b6 100644
--- a/pages/applications/_meta.jp.json
+++ b/pages/applications/_meta.jp.json
@@ -1,4 +1,5 @@
 {
     "pal": "PAL（プログラム支援言語モデル）",
-    "generating": "データ生成"
+    "generating": "データ生成",
+    "workplace_casestudy": "Graduate Job Classification Case Study"
 }
\ No newline at end of file
diff --git a/pages/applications/_meta.pt.json b/pages/applications/_meta.pt.json
index e34b985..b27c063 100644
--- a/pages/applications/_meta.pt.json
+++ b/pages/applications/_meta.pt.json
@@ -1,4 +1,5 @@
 {
     "pal": "Program-Aided Language Models",
-    "generating": "Generating Data"
+    "generating": "Generating Data",
+    "workplace_casestudy": "Graduate Job Classification Case Study"
 }
\ No newline at end of file
diff --git a/pages/applications/_meta.zh.json b/pages/applications/_meta.zh.json
index e34b985..b27c063 100644
--- a/pages/applications/_meta.zh.json
+++ b/pages/applications/_meta.zh.json
@@ -1,4 +1,5 @@
 {
     "pal": "Program-Aided Language Models",
-    "generating": "Generating Data"
+    "generating": "Generating Data",
+    "workplace_casestudy": "Graduate Job Classification Case Study"
 }
\ No newline at end of file
diff --git a/pages/applications/workplace_casestudy.jp.mdx b/pages/applications/workplace_casestudy.jp.mdx
new file mode 100644
index 0000000..92e08b7
--- /dev/null
+++ b/pages/applications/workplace_casestudy.jp.mdx
@@ -0,0 +1,3 @@
+# Graduate Job Classification Case Study
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/applications/workplace_casestudy.pt.mdx b/pages/applications/workplace_casestudy.pt.mdx
new file mode 100644
index 0000000..92e08b7
--- /dev/null
+++ b/pages/applications/workplace_casestudy.pt.mdx
@@ -0,0 +1,3 @@
+# Graduate Job Classification Case Study
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/applications/workplace_casestudy.zh.mdx b/pages/applications/workplace_casestudy.zh.mdx
new file mode 100644
index 0000000..92e08b7
--- /dev/null
+++ b/pages/applications/workplace_casestudy.zh.mdx
@@ -0,0 +1,3 @@
+# Graduate Job Classification Case Study
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file

From e585b40feb29465874587ab3e753571714bfa815 Mon Sep 17 00:00:00 2001
From: qumc <108912876+qumc@users.noreply.github.com>
Date: Wed, 5 Apr 2023 22:59:10 -0400
Subject: [PATCH 12/24] Update settings.zh.mdx

---
 pages/introduction/settings.zh.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pages/introduction/settings.zh.mdx b/pages/introduction/settings.zh.mdx
index 9dd3dcd..5b9a297 100644
--- a/pages/introduction/settings.zh.mdx
+++ b/pages/introduction/settings.zh.mdx
@@ -4,7 +4,7 @@
 
 **Temperature**：简单来说，`temperature` 的参数值越小，模型就会返回最确定的一个结果。如果调高该参数值，大语言模型可能会返回更随机的结果，也就是说这可能会带来更多样化或更具创造性的产出。我们目前也在增加其他可能 token 的权重。在实际应用方面，对于质量保障（QA）等任务，我们可以设置更低的 `temperature` 值，以促使模型基于事实返回更真实和简洁的结果。 对于诗歌生成或其他创造性任务，你可以适当调高 `temperature` 参数值。
 
-同样，使用 `top_p`（与 `temperature` 一起称为核采样的技术），可以用来控制模型返回结果的真实性。如果你需要准确和事实的答案，就把参数值调低。如果你想要更多样化的答案，就把参数值调高一些。
+**Top_p**：同样，使用 `top_p`（与 `temperature` 一起称为核采样的技术），可以用来控制模型返回结果的真实性。如果你需要准确和事实的答案，就把参数值调低。如果你想要更多样化的答案，就把参数值调高一些。
 
 一般建议是改变其中一个参数就行，不用两个都调整。
 

From 40c146107c60290f23974e96aa83f4ae2ec9e02f Mon Sep 17 00:00:00 2001
From: rabbuttz <49971163+rabbuttz@users.noreply.github.com>
Date: Thu, 6 Apr 2023 15:59:51 +0900
Subject: [PATCH 13/24] fix japanese translation

edited the translation of the sentence "Let's work this out it a step by step to be sure we have the right answer".
---
 pages/techniques/ape.jp.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/techniques/ape.jp.mdx b/pages/techniques/ape.jp.mdx
index 27b6cde..e15a341 100644
--- a/pages/techniques/ape.jp.mdx
+++ b/pages/techniques/ape.jp.mdx
@@ -14,7 +14,7 @@ import APECOT from '../../img/ape-zero-shot-cot.png'
 
 APEは、人間が設計した「一緒にステップバイステップで考えてみましょう」というプロンプトよりも優れたゼロショットCoTプロンプトを発見しました（[Kojima et al.、2022](https://arxiv.org/abs/2205.11916)）。
 
-「一緒にステップバイステップで作業し、正しい答えを確認するために」のプロンプトは、思考の連鎖を引き起こし、MultiArithおよびGSM8Kベンチマークのパフォーマンスを向上させます。
+「正しい答えを得るために、ステップバイステップで考えてみましょう。」のプロンプトは、思考の連鎖を引き起こし、MultiArithおよびGSM8Kベンチマークのパフォーマンスを向上させます。
 
 <Screenshot src={APECOT} alt="APECOT" />
 画像出典：[Zhou et al.,（2022年）](https://arxiv.org/abs/2211.01910)
@@ -23,4 +23,4 @@ APEは、人間が設計した「一緒にステップバイステップで考
 
 - [AutoPrompt](https://arxiv.org/abs/2010.15980) - 勾配誘導型の検索に基づいて、多様なタスクのためのプロンプトを自動的に作成するアプローチを提案します。
 - [Prefix Tuning](https://arxiv.org/abs/2101.00190) - NLGタスクのためのトレーニング可能な連続プレフィックスを前置する、ファインチューニングの軽量な代替案です。
-- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - 逆伝播を通じてソフトプロンプトを学習するメカニズムを提案します。
\ No newline at end of file
+- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - 逆伝播を通じてソフトプロンプトを学習するメカニズムを提案します。

From 61fab8d247cdda0061b34dc2816abd627a147773 Mon Sep 17 00:00:00 2001
From: fangd123 <fangd123@qq.com>
Date: Thu, 6 Apr 2023 23:07:50 +0800
Subject: [PATCH 14/24] added chinese menu translation

---
 pages/_meta.zh.json              | 28 ++++++++++++++--------------
 pages/applications/_meta.zh.json |  6 +++---
 pages/introduction/_meta.zh.json | 10 +++++-----
 pages/risks/_meta.zh.json        |  6 +++---
 pages/techniques/_meta.zh.json   | 20 ++++++++++----------
 5 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/pages/_meta.zh.json b/pages/_meta.zh.json
index 73d2b9b..33359d3 100644
--- a/pages/_meta.zh.json
+++ b/pages/_meta.zh.json
@@ -1,25 +1,25 @@
 {
-  "index": "Prompt Engineering",
-  "introduction": "Introduction",
-  "techniques": "Techniques",
-  "applications": "Applications",
-  "models": "Models",
-  "risks": "Risks & Misuses",
-  "papers": "Papers",
-  "tools": "Tools",
-  "notebooks": "Notebooks",
-  "datasets": "Datasets",
-  "readings": "Additional Readings",
+  "index": "提示工程指南",
+  "introduction": "提示工程简介",
+  "techniques": "提示技术",
+  "applications": "提示应用",
+  "models": "模型",
+  "risks": "风险和误用",
+  "papers": "论文",
+  "tools": "工具和库",
+  "notebooks": "Prompt Engineering 笔记本",
+  "datasets": "数据集",
+  "readings": "阅读推荐",
   "about": {
-    "title": "About",
+    "title": "关于",
     "type": "page"
   },
   "course":{
-    "title": "Prompt Engineering Course",
+    "title": "提示工程课程",
     "type": "page"
   },
   "contact": {
-    "title": "Contact ↗",
+    "title": "联系我们 ↗",
     "type": "page",
     "href": "https://twitter.com/dair_ai",
     "newWindow": true
diff --git a/pages/applications/_meta.zh.json b/pages/applications/_meta.zh.json
index b27c063..9fcc1f3 100644
--- a/pages/applications/_meta.zh.json
+++ b/pages/applications/_meta.zh.json
@@ -1,5 +1,5 @@
 {
-    "pal": "Program-Aided Language Models",
-    "generating": "Generating Data",
-    "workplace_casestudy": "Graduate Job Classification Case Study"
+    "pal": "程序辅助语言模型",
+    "generating": "生成数据",
+    "workplace_casestudy": "毕业生工作分类案例研究"
 }
\ No newline at end of file
diff --git a/pages/introduction/_meta.zh.json b/pages/introduction/_meta.zh.json
index 52372db..ee141c9 100644
--- a/pages/introduction/_meta.zh.json
+++ b/pages/introduction/_meta.zh.json
@@ -1,8 +1,8 @@
 {
-    "settings": "LLM Settings",
-    "basics": "Basics of Prompting",
-    "elements": "Prompt Elements",
-    "tips": "General Tips for Designing Prompts",
-    "examples": "Examples of Prompts"
+    "settings": "大语言模型设置",
+    "basics": "基本概念",
+    "elements": "提示词要素",
+    "tips": "设计提示的通用技巧",
+    "examples": "提示词示例"
 }
   
\ No newline at end of file
diff --git a/pages/risks/_meta.zh.json b/pages/risks/_meta.zh.json
index 29a5ff4..8fb8695 100644
--- a/pages/risks/_meta.zh.json
+++ b/pages/risks/_meta.zh.json
@@ -1,6 +1,6 @@
 {
-    "adversarial": "Adversarial Prompting",
-    "factuality": "Factuality",
-    "biases": "Biases"
+    "adversarial": "对抗性提示",
+    "factuality": "真实性",
+    "biases": "偏见"
 }
   
\ No newline at end of file
diff --git a/pages/techniques/_meta.zh.json b/pages/techniques/_meta.zh.json
index 3a672e7..6e1b3fd 100644
--- a/pages/techniques/_meta.zh.json
+++ b/pages/techniques/_meta.zh.json
@@ -1,14 +1,14 @@
 {
-    "zeroshot": "Zero-shot Prompting",
-    "fewshot": "Few-shot Prompting",
-    "cot": "Chain-of-Thought Prompting",
-    "consistency": "Self-Consistency",
-    "knowledge": "Generate Knowledge Prompting",
-    "ape": "Automatic Prompt Engineer",
+    "zeroshot": "零样本提示",
+    "fewshot": "少样本提示",
+    "cot": "链式思考（CoT）提示",
+    "consistency": "自我一致性",
+    "knowledge": "生成知识提示",
+    "ape": "自动提示工程师",
     "activeprompt": "Active-Prompt",
-    "dsp": "Directional Stimulus Prompting",
-    "react": "ReAct",
-    "multimodalcot": "Multimodal CoT",
-    "graph": "Graph Prompting"
+    "dsp": "方向性刺激提示",
+    "react": "ReAct框架",
+    "multimodalcot": "多模态思维链提示方法",
+    "graph": "基于图的提示"
 }
   
\ No newline at end of file

From b59e39958f42ee16440560a567fa421e16dec5b8 Mon Sep 17 00:00:00 2001
From: Cleisson Barbosa <32576001+cleissonbarbosa@users.noreply.github.com>
Date: Thu, 6 Apr 2023 13:59:43 -0300
Subject: [PATCH 15/24] Fix pt translation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

"The sky is" to "O céu é"
---
 pages/introduction/basics.pt.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/introduction/basics.pt.mdx b/pages/introduction/basics.pt.mdx
index d37a651..153f8bc 100644
--- a/pages/introduction/basics.pt.mdx
+++ b/pages/introduction/basics.pt.mdx
@@ -18,7 +18,7 @@ azul
 O céu é azul em um dia claro. Em um dia nublado, o céu pode ser cinza ou branco.
 ```
 
-Como você pode ver, o modelo de linguagem gera uma continuação de strings que fazem sentido no contexto `"The sky is"`. A saída pode ser inesperada ou distante da tarefa que queremos realizar.
+Como você pode ver, o modelo de linguagem gera uma continuação de strings que fazem sentido no contexto `"O céu é"`. A saída pode ser inesperada ou distante da tarefa que queremos realizar.
 
 Este exemplo básico também destaca a necessidade de fornecer mais contexto ou instruções sobre o que especificamente queremos alcançar.
 
@@ -111,4 +111,4 @@ Que espetáculo horrível! //
 Negativo
 ```
 
-Os prompts de poucos disparos permitem o aprendizado no contexto, que é a capacidade dos modelos de linguagem de aprender tarefas dadas algumas demonstrações.
\ No newline at end of file
+Os prompts de poucos disparos permitem o aprendizado no contexto, que é a capacidade dos modelos de linguagem de aprender tarefas dadas algumas demonstrações.

From 03db33dfc34af65a286db0dbfdcec1f700f77ee9 Mon Sep 17 00:00:00 2001
From: komori556 <totoronomori556@gmail.com>
Date: Fri, 7 Apr 2023 15:33:47 +0900
Subject: [PATCH 16/24] fix-incorrect-translation-example-page

---
 pages/introduction/examples.jp.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pages/introduction/examples.jp.mdx b/pages/introduction/examples.jp.mdx
index 3e20d24..0c7409e 100644
--- a/pages/introduction/examples.jp.mdx
+++ b/pages/introduction/examples.jp.mdx
@@ -118,7 +118,7 @@ Neutral
 
 *プロンプト：*
 ```
-テキストを中立、否定的、または肯定的に分類してください。
+テキストをneutral、negative、またはpositiveに分類してください。
 
 テキスト：先日の休暇はまずまずでした。
 所感: neutral 

From fb9f507cadafbb8a6d7b65087c949bb6423252d2 Mon Sep 17 00:00:00 2001
From: komori556 <totoronomori556@gmail.com>
Date: Fri, 7 Apr 2023 17:20:04 +0900
Subject: [PATCH 17/24] fix-incorrect-translation-tips-page

---
 pages/introduction/tips.jp.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pages/introduction/tips.jp.mdx b/pages/introduction/tips.jp.mdx
index 58e162f..2a6711d 100644
--- a/pages/introduction/tips.jp.mdx
+++ b/pages/introduction/tips.jp.mdx
@@ -50,7 +50,7 @@ Place: <comma_separated_list_of_company_names>
 
 *出力：*
 ```
-Place: Champalimaud Centre for the Unknown, Lisbon
+Place: リスボンのシャンパリマウド・センター・フォー・ジ・アンノウン
 ```
 
 入力テキストは、[このNature記事](https://www.nature.com/articles/d41586-023-00509-z)から取得されています。

From 1852f11abfcf1509e8f3dd2c0246cc0de7c6bae8 Mon Sep 17 00:00:00 2001
From: nsfisis <nsfisis@gmail.com>
Date: Sat, 8 Apr 2023 01:44:02 +0900
Subject: [PATCH 18/24] Fix Japanese translations

---
 pages/introduction/basics.jp.mdx | 2 +-
 pages/introduction/tips.jp.mdx   | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/pages/introduction/basics.jp.mdx b/pages/introduction/basics.jp.mdx
index 0328953..2c163eb 100644
--- a/pages/introduction/basics.jp.mdx
+++ b/pages/introduction/basics.jp.mdx
@@ -18,7 +18,7 @@
 晴れた日には空は青く、曇った日には空は灰色や白色になることがあります。
 ```
 
-おわかりのように、言語モデルは、文脈「"空が"」に合った文字列の続きを出力します。出力は予期しないものであり、私たちが達成したいタスクからはかけ離れている可能性があります。
+おわかりのように、言語モデルは、文脈「"空が"」に合った文字列の続きを出力します。出力は、予期しないものであったり、私たちが達成したいタスクからかけ離れていたりする可能性があります。
 
 この基本例は、より多くの文脈や指示を提供する必要性を強調するものでもあります。
 
diff --git a/pages/introduction/tips.jp.mdx b/pages/introduction/tips.jp.mdx
index 58e162f..380435a 100644
--- a/pages/introduction/tips.jp.mdx
+++ b/pages/introduction/tips.jp.mdx
@@ -3,11 +3,11 @@
 プロンプトを設計する際には以下のことに注意するとよいでしょう。
 
 ### 簡単に始める
-プロンプトの設計を始める際には、最適な結果を得るために多くの実験が必要な反復的なプロセスであることを念頭に置く必要があります。OpenAIやCohereのようなシンプルなプレイグラウンドから始めると良いでしょう。
+プロンプトの設計を始める際には、プロンプトの設計が、最適な結果を得るために多くの実験を必要とする反復的なプロセスであることを念頭に置く必要があります。OpenAIやCohereのようなシンプルなプレイグラウンドから始めると良いでしょう。
 
 シンプルなプロンプトから始め、結果を向上させるために要素や文脈を追加していくことができます。そのためにはプロンプトのバージョン管理が重要です。このガイドを読むと、具体性、簡潔さ、明確さがより良い結果をもたらすことがわかるでしょう。
 
-多くの異なるサブタスクを含む大きなタスクがある場合、タスクをよりシンプルなサブタスクに分解し、結果が改善されるにつれて徐々に構築していくことができます。これにより、プロンプトの設計プロセスにあまり複雑さを加えることがなくなります。
+多くの異なるサブタスクを含む大きなタスクがある場合、タスクをよりシンプルなサブタスクに分解し、結果が改善されるにつれて徐々に構築していくことができます。こうすることで、プロンプトの設計プロセスが複雑になりすぎるのを避けられます。
 
 ### 指示
 「書く」「分類する」「要約する」「翻訳する」「並べ替える」などのコマンドを使用して、モデルに達成したいことを指示することで、さまざまなシンプルなタスクに対する効果的なプロンプトを設計することができます。
@@ -33,7 +33,7 @@ Text: "hello!"
 ### 特異性
 モデルに実行してほしい指示やタスクについて、非常に具体的に説明してください。プロンプトが詳細で具体的であるほど、結果はよくなります。特定の出力やスタイルを望む場合には、特に重要です。より良い結果をもたらすトークンやキーワードはありません。良いフォーマットと詳細なプロンプトを用意することが重要です。実際、プロンプトに例を提供することは、特定のフォーマットで出力を得るために非常に効果的です。
 
-プロンプトを設計する際には、プロンプトの長さに関する制限があるため、考慮する必要があります。どの程度具体的かつ詳細にするかを考える必要があります。余計な詳細を含めることは必ずしも良いアプローチではありません。詳細は関連性があり、課題に貢献する必要があります。これは多くの実験と反復を必要とすることです。アプリケーションに最適なプロンプトを最適化するために、多くの実験と反復をお勧めします。
+プロンプトの長さには制限があるため、プロンプトの設計時にはその長さを念頭に置かねばなりません。どの程度具体的かつ詳細にするかを考える必要があります。余計な詳細を含めることは必ずしも良いアプローチではありません。詳細は関連性があり、課題に貢献する必要があります。これは多くの実験と反復を必要とすることです。アプリケーションに最適なプロンプトを最適化するために、多くの実験と反復をお勧めします。
 
 例えば、次のテキストから特定の場所の名前を抽出する簡単なプロンプトを試してみましょう。
 
@@ -57,7 +57,7 @@ Place: Champalimaud Centre for the Unknown, Lisbon
 
 ### 不正確さを避ける
 
-上記の詳細でフォーマットを改善するヒントに加えて、プロンプトについて賢くなりすぎて、不正確な説明を作り出すことが容易になります。具体的で直接的である方が良い結果が得られます。ここでの類似性は、効果的なコミュニケーションと非常に類似しています--直接的であるほど、効果的にメッセージが伝わります。
+詳細に記述したりフォーマットを改善したりする上記のようなヒントを考慮すると、プロンプトを巧みに操ろうとしたり、不正確な説明を作り出してしまったりするといった罠へ陥りやすくなります。具体的で直接的である方が良い結果が得られます。ここでの類似性は、効果的なコミュニケーションと非常に類似しています--直接的であるほど、効果的にメッセージが伝わります。
 
 例えば、プロンプトエンジニアリングの概念を学びたいと思うかもしれません。
 

From 875cfb51ade7da7b9df10dca3ed36845f175ec55 Mon Sep 17 00:00:00 2001
From: Taner Sekmen <tanersekmen@gmail.com>
Date: Sat, 8 Apr 2023 11:23:03 +0300
Subject: [PATCH 19/24] add turkish language to the page

---
 pages/_met.tr.json                            |  28 +++
 pages/about.tr.mdx                            |  11 ++
 pages/applications.tr.mdx                     |   9 +
 pages/applications/_meta.tr.json              |   5 +
 pages/applications/generating.tr.mdx          |  44 +++++
 pages/applications/pal.tr.mdx                 | 106 +++++++++++
 pages/applications/workplace_casestudy.tr.mdx |  57 ++++++
 pages/course.tr.mdx                           |   9 +
 pages/datasets.tr.mdx                         |  12 ++
 pages/index.tr.mdx                            |   9 +
 pages/introduction.tr.mdx                     |   7 +
 pages/introduction/_meta.tr.json              |   8 +
 pages/introduction/basics.tr.mdx              | 114 ++++++++++++
 pages/introduction/elements.tr.mdx            |  15 ++
 pages/introduction/examples.tr.mdx            |   3 +
 pages/introduction/settings.tr.mdx            |  11 ++
 pages/introduction/tips.tr.mdx                |   3 +
 pages/models.tr.mdx                           |   9 +
 pages/models/_meta.tr.json                    |   8 +
 pages/models/collection.tr.mdx                |  65 +++++++
 pages/models/flan.tr.mdx                      |   3 +
 pages/models/gpt-4.tr.mdx                     |   3 +
 pages/models/llama.tr.mdx                     |  43 +++++
 pages/notebooks.tr.mdx                        |  11 ++
 pages/papers.tr.mdx                           | 174 ++++++++++++++++++
 pages/readings.tr.mdx                         | 114 ++++++++++++
 pages/risks.tr.mdx                            |  12 ++
 pages/risks/_meta.tr.json                     |   6 +
 pages/risks/adversarial.tr.mdx                |   3 +
 pages/risks/biases.tr.mdx                     |  98 ++++++++++
 pages/risks/factuality.en.mdx                 |   4 +-
 pages/risks/factuality.tr.mdx                 |  34 ++++
 pages/techniques.tr.mdx                       |   5 +
 pages/techniques/_meta.tr.json                |  14 ++
 pages/techniques/activeprompt.tr.mdx          |  12 ++
 pages/techniques/ape.tr.mdx                   |  26 +++
 pages/techniques/consistency.tr.mdx           |   3 +
 pages/techniques/cot.tr.mdx                   |   3 +
 pages/techniques/dsp.tr.mdx                   |  16 ++
 pages/techniques/fewshot.tr.mdx               |   3 +
 pages/techniques/graph.tr.mdx                 |   5 +
 pages/techniques/knowledge.tr.mdx             |   3 +
 pages/techniques/multimodalcot.tr.mdx         |  15 ++
 pages/techniques/react.tr.mdx                 |  15 ++
 pages/techniques/zeroshot.tr.mdx              |  21 +++
 pages/tools.tr.mdx                            |  41 +++++
 46 files changed, 1218 insertions(+), 2 deletions(-)
 create mode 100644 pages/_met.tr.json
 create mode 100644 pages/about.tr.mdx
 create mode 100644 pages/applications.tr.mdx
 create mode 100644 pages/applications/_meta.tr.json
 create mode 100644 pages/applications/generating.tr.mdx
 create mode 100644 pages/applications/pal.tr.mdx
 create mode 100644 pages/applications/workplace_casestudy.tr.mdx
 create mode 100644 pages/course.tr.mdx
 create mode 100644 pages/datasets.tr.mdx
 create mode 100644 pages/index.tr.mdx
 create mode 100644 pages/introduction.tr.mdx
 create mode 100644 pages/introduction/_meta.tr.json
 create mode 100644 pages/introduction/basics.tr.mdx
 create mode 100644 pages/introduction/elements.tr.mdx
 create mode 100644 pages/introduction/examples.tr.mdx
 create mode 100644 pages/introduction/settings.tr.mdx
 create mode 100644 pages/introduction/tips.tr.mdx
 create mode 100644 pages/models.tr.mdx
 create mode 100644 pages/models/_meta.tr.json
 create mode 100644 pages/models/collection.tr.mdx
 create mode 100644 pages/models/flan.tr.mdx
 create mode 100644 pages/models/gpt-4.tr.mdx
 create mode 100644 pages/models/llama.tr.mdx
 create mode 100644 pages/notebooks.tr.mdx
 create mode 100644 pages/papers.tr.mdx
 create mode 100644 pages/readings.tr.mdx
 create mode 100644 pages/risks.tr.mdx
 create mode 100644 pages/risks/_meta.tr.json
 create mode 100644 pages/risks/adversarial.tr.mdx
 create mode 100644 pages/risks/biases.tr.mdx
 create mode 100644 pages/risks/factuality.tr.mdx
 create mode 100644 pages/techniques.tr.mdx
 create mode 100644 pages/techniques/_meta.tr.json
 create mode 100644 pages/techniques/activeprompt.tr.mdx
 create mode 100644 pages/techniques/ape.tr.mdx
 create mode 100644 pages/techniques/consistency.tr.mdx
 create mode 100644 pages/techniques/cot.tr.mdx
 create mode 100644 pages/techniques/dsp.tr.mdx
 create mode 100644 pages/techniques/fewshot.tr.mdx
 create mode 100644 pages/techniques/graph.tr.mdx
 create mode 100644 pages/techniques/knowledge.tr.mdx
 create mode 100644 pages/techniques/multimodalcot.tr.mdx
 create mode 100644 pages/techniques/react.tr.mdx
 create mode 100644 pages/techniques/zeroshot.tr.mdx
 create mode 100644 pages/tools.tr.mdx

diff --git a/pages/_met.tr.json b/pages/_met.tr.json
new file mode 100644
index 0000000..b94eca7
--- /dev/null
+++ b/pages/_met.tr.json
@@ -0,0 +1,28 @@
+{
+    "index": "Prompt Engineering",
+    "introduction": "Introduction",
+    "techniques": "Techniques",
+    "applications": "Applications",
+    "models": "Models",
+    "risks": "Risks & Misuses",
+    "papers": "Papers",
+    "tools": "Tools",
+    "notebooks": "Notebooks",
+    "datasets": "Datasets",
+    "readings": "Additional Readings",
+    "about": {
+      "title": "About",
+      "type": "page"
+    },
+    "course":{
+      "title": "Prompt Engineering Course",
+      "type": "page"
+    },
+    "contact": {
+      "title": "Contact ↗",
+      "type": "page",
+      "href": "https://twitter.com/dair_ai",
+      "newWindow": true
+    }
+  }
+  
\ No newline at end of file
diff --git a/pages/about.tr.mdx b/pages/about.tr.mdx
new file mode 100644
index 0000000..969620c
--- /dev/null
+++ b/pages/about.tr.mdx
@@ -0,0 +1,11 @@
+# Hakkında
+
+Prompt Engineering Guide, [DAIR.AI](https://github.com/dair-ai) tarafından hazırlanan bir projedir. Araştırmacıları ve uygulamacıları hızlı mühendislik konusunda eğitmeyi amaçlamaktadır.
+
+DAIR.AI, AI araştırmasını, eğitimini ve teknolojilerini demokratikleştirmeyi amaçlamaktadır. Misyonumuz, yeni nesil yapay zeka yenilikçilerini ve yaratıcılarını mümkün kılmaktır.
+
+Topluluğun katkılarını memnuniyetle karşılıyoruz. Düzenle düğmelerini arayın.
+
+Lisans bilgileri [burada](https://github.com/dair-ai/Prompt-Engineering-Guide#license).
+
+[OpenAI CookBook](https://github.com/openai/openai-cookbook), [Pretrain, Prompt, Predict](http://pretrain.nlpedia.ai/), [Learn] gibi birçok açık kaynaktan ilham alıyoruz. Yönlendirme](https://learnprompting.org/) ve diğerleri.
\ No newline at end of file
diff --git a/pages/applications.tr.mdx b/pages/applications.tr.mdx
new file mode 100644
index 0000000..1926066
--- /dev/null
+++ b/pages/applications.tr.mdx
@@ -0,0 +1,9 @@
+# İstemci Uygulamaları
+
+import { Callout } from 'nextra-theme-docs'
+
+Bu bölümde, yararlı ve daha gelişmiş görevleri gerçekleştirmek için hızlı mühendisliği kullanabileceğimiz bazı gelişmiş ve ilginç yolları ele alacağız.
+
+<Callout emoji="⚠️">
+  Bu bölüm yoğun geliştirme aşamasındadır.
+</Callout>
\ No newline at end of file
diff --git a/pages/applications/_meta.tr.json b/pages/applications/_meta.tr.json
new file mode 100644
index 0000000..8c23b98
--- /dev/null
+++ b/pages/applications/_meta.tr.json
@@ -0,0 +1,5 @@
+{
+    "pal": "Program-Aided Language Models",
+    "generating": "Generating Data",
+    "workplace_casestudy": "Graduate Job Classification Case Study"
+}
diff --git a/pages/applications/generating.tr.mdx b/pages/applications/generating.tr.mdx
new file mode 100644
index 0000000..0ad3f74
--- /dev/null
+++ b/pages/applications/generating.tr.mdx
@@ -0,0 +1,44 @@
+# Veri Oluşturma
+LLM'ler tutarlı bir metin oluşturma konusunda güçlü yeteneklere sahiptir. Etkili prompt stratejileri kullanarak, model daha iyi, tutarlı ve daha gerçekçi yanıtlar üretmeye yönlendirebilir. LLM'ler ayrıca, örneğin duygu sınıflandırıcısı için hızlı örnekler oluşturmak gibi tüm çeşitli deneyler ve değerlendirmeler için gerçekten faydalı olan verilerin üretilmesinde özellikle faydalı olabilir.
+
+*Komut İstemi:*
+```
+Duygu analizi için 10 örnek üretin. Örnekler olumlu veya olumsuz olarak kategorize edilsin. 2 olumsuz ve 8 olumlu örnek üretin. Örnekler için bu formatı kullanın.
+S: <cümle>
+C: <duygu>
+```
+
+*Çıktı:*
+```
+S: Şimdiye kadarki en iyi haberi aldım!
+C: Olumlu
+
+S: İş yerinde zam aldık!
+C: Olumlu
+
+S: Bugün başardıklarımla gurur duyuyorum.
+C: Olumlu
+
+S: Şimdiye kadarki en iyi günü yaşıyorum!
+C: Olumlu
+
+S: Gerçekten hafta sonunu dört gözle bekliyorum.
+C: Olumlu
+
+S: Şimdiye kadarki en iyi hediyeyi aldım!
+C: Olumlu
+
+S: Şu an çok mutluyum.
+C: Olumlu
+
+S: Böyle harika bir aileye sahip olduğum için çok şanslıyım.
+C: Olumlu
+
+S: Dışarda hava çok kasvetli.
+C: Olumsuz
+
+S: Az önce korkunç bir haber aldım.
+C: Olumsuz
+```
+
+Bu çok kullanışlı. Bu örneği aslında kılavuzun başka bir bölümünde farklı bir test için kullanıyoruz.
\ No newline at end of file
diff --git a/pages/applications/pal.tr.mdx b/pages/applications/pal.tr.mdx
new file mode 100644
index 0000000..5646d02
--- /dev/null
+++ b/pages/applications/pal.tr.mdx
@@ -0,0 +1,106 @@
+# PAL (Program-Aided Language Models)
+ 
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import PAL from '../../img/pal.png'
+
+[Gao et al., (2022)](https://arxiv.org/abs/2211.10435) doğal dil problemlerini okumak ve ara akıl yürütme adımları olarak programlar oluşturmak için LLM'leri kullanan bir yöntem sunar. 
+Türetilmiş, program destekli dil modelleri (PAL), çözüm elde etmek için serbest biçimli metin kullanmak yerine çözüm adımını Python yorumlayıcısı gibi programlı bir çalışma zamanına aktardığı için düşünce zinciri yönlendirmesinden farklıdır.
+
+<Screenshot src={PAL} alt="PAL" />
+Image Source: [Gao et al., (2022)](https://arxiv.org/abs/2211.10435)
+
+LangChain ve OpenAI GPT-3 kullanan bir örneğe bakalım. Sorulan soruyu yorumlayabilen ve Python yorumlayıcısından yararlanarak yanıt sağlayabilen basit bir uygulama geliştirmekle ilgileniyoruz.
+
+Spesifik olarak, tarihin anlaşılmasını gerektiren soruları yanıtlamak için LLM kullanımına izin veren bir işlev oluşturmakla ilgileniyoruz. LLM'ye [buradan](https://github.com/reasoning-machines/pal/blob/main/pal/prompt/date_understanding_prompt.py) benimsenen birkaç örneği içeren bir bilgi istemi sağlayacağız.
+
+İhtiyacımız olan kütüphaneler:
+
+```python
+import openai
+from datetime import datetime
+from dateutil.relativedelta import relativedelta
+import os
+from langchain.llms import OpenAI
+from dotenv import load_dotenv
+```
+
+Önce birkaç şeyi yapılandıralım:
+
+```python
+load_dotenv()
+
+# API yapılandırma
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# LangChain için
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+```
+
+Kurulum modeli örneği:
+
+```python
+llm = OpenAI(model_name='text-davinci-003', temperature=0)
+```
+
+Kurulum istemi + soru:
+
+```python
+question = "Today is 27 February 2023. I was born exactly 25 years ago. What is the date I was born in MM/DD/YYYY?"
+
+DATE_UNDERSTANDING_PROMPT = """
+# S: 36 saat sonra 2015 geliyor. AA/GG/YYYY olarak bugünden bir hafta sonraki tarih nedir?
+# 2015 yılı 36 saat sonra geliyorsa, bugün 36 saat öncesidir.
+today = datetime(2015, 1, 1) - relativedelta(hours=36)
+# Bugünden bir hafta sonra,
+one_week_from_today = today + relativedelta(weeks=1)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+one_week_from_today.strftime('%m/%d/%Y')
+# S: 2019'un ilk günü Salı ve bugün 2019'un ilk Pazartesi günü. Bugünün AA/GG/YYYY cinsinden tarihi nedir?
+# 2019'un ilk günü Salı günü olup bugün de 2019'un ilk Pazartesi günüyse, bugün 6 gün sonradır.
+today = datetime(2019, 1, 1) + relativedelta(days=6)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+today.strftime('%m/%d/%Y')
+# S: Konserin 01/06/1943 tarihinde yapılması planlanmıştı, ancak bir gün ertelenmiştir. AA/GG/YYYY cinsinden 10 gün önceki tarih nedir?
+# Konser 01/06/1943 tarihinde planlanmış, ancak bugüne bir gün ertelenmişse, bugün bir gün sonradır.
+today = datetime(1943, 6, 1) + relativedelta(days=1)
+# 10 gün önce,
+ten_days_ago = today - relativedelta(days=10)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+ten_days_ago.strftime('%m/%d/%Y')
+# S: Bugün 19/4/1969. AA/GG/YYYY cinsinden 24 saat sonraki tarih nedir?
+# Bugün 19/4/1969.
+today = datetime(1969, 4, 19)
+# 24 hours later,
+later = today + relativedelta(hours=24)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+today.strftime('%m/%d/%Y')
+# S: Jane bugünün 11/3/2002 olduğunu düşündü, ama aslında bugün 12 Mart yani 1 gün sonra. AA/GG/YYYY cinsinden 24 saat sonraki tarih nedir?
+# Jane bugünün 11/3/2002 olduğunu düşündüyse ama aslında bugün 12 Mart ise, o zaman bugün 1/3/2002'dir.
+today = datetime(2002, 3, 12)
+# 24 saat sonra,
+later = today + relativedelta(hours=24)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+later.strftime('%m/%d/%Y')
+# S: Jane, 2001'de Şubat ayının son gününde doğdu. Bugün onun 16.yaş günü. AA/GG/YYYY cinsinden dünkü tarih nedir?
+# Jane 2001'de Şubat ayının son gününde doğduysa ve bugün onun 16.yaş günü ise, o zaman bugün 16 yıl sonradır.
+today = datetime(2001, 2, 28) + relativedelta(years=16)
+# Dün,
+yesterday = today - relativedelta(days=1)
+# %m/%d/%Y ile biçimlendirilen yanıt:
+yesterday.strftime('%m/%d/%Y')
+# S: {question}
+""".strip() + '\n'
+```
+
+```python
+llm_out = llm(DATE_UNDERSTANDING_PROMPT.format(question=question))
+print(llm_out)
+```
+
+```python
+exec(llm_out)
+print(born)
+```
+
+Aşağıdaki çıktıyı verecektir: `27/02/1998`
\ No newline at end of file
diff --git a/pages/applications/workplace_casestudy.tr.mdx b/pages/applications/workplace_casestudy.tr.mdx
new file mode 100644
index 0000000..de8e605
--- /dev/null
+++ b/pages/applications/workplace_casestudy.tr.mdx
@@ -0,0 +1,57 @@
+# Mezun İş Sınıflandırma Vaka Çalışması
+
+[Clavié et al., 2023](https://arxiv.org/abs/2303.07142) bir üretim sisteminde orta ölçekli bir metin sınıflandırma kullanım durumuna uygulanan bilgi istemi mühendisliği üzerine bir örnek olay çalışması sağlayın. Bir işin gerçek bir "giriş seviyesi iş" olup olmadığını, yeni mezunlar için uygun olup olmadığını sınıflandırma görevini kullanarak, bir dizi hızlı mühendislik tekniğini değerlendirdiler ve sonuçlarını GPT-3.5 ('gpt-3.5-turbo) kullanarak raporladılar.').
+
+Çalışma, LLM'lerin, DeBERTa-V3'teki son derece güçlü bir temel dahil, test edilen diğer tüm modellerden daha iyi performans gösterdiğini gösteriyor. "gpt-3.5-turbo" ayrıca tüm temel ölçümlerde eski GPT3 türevlerinden önemli ölçüde daha iyi performans gösterir, ancak bir şablona bağlı kalma yeteneği diğer değişkenlerden daha kötü göründüğü için ek çıktı ayrıştırması gerektirir.
+
+Hızlı mühendislik yaklaşımlarının temel bulguları şunlardır:
+
+- Uzman bilgisinin gerekli olmadığı bunun gibi görevler için, Few-shot CoT yönlendirmesi, tüm deneylerde Zero-shot yönlendirmesinden daha kötü performans gösterdi.
+- İstemin doğru muhakemeyi ortaya çıkarma üzerindeki etkisi çok büyüktür. Modelden belirli bir işi sınıflandırmasını istemek, 65.6'lık bir F1 puanıyla sonuçlanırken, istem sonrası mühendislik modeli, 91.7'lik bir F1 puanı elde eder.
+- Modeli bir şablona bağlı kalmaya zorlamak her durumda performansı düşürür (bu davranış, kağıdın arkasında olan GPT-4 ile erken testlerde kaybolur).
+- Birçok küçük değişikliğin performans üzerinde çok büyük bir etkisi vardır.
+  - Aşağıdaki tablolar, test edilen tam değişiklikleri göstermektedir.
+  - Talimatları düzgün bir şekilde vermek ve kilit noktaları tekrarlamak en büyük performans faktörü gibi görünüyor.
+  - Modele bir (insan) adı vermek ve ona bu şekilde atıfta bulunmak kadar basit bir şey, F1 puanını 0,6 puan artırdı.
+
+### Bilgi İstemi Değişiklikleri Test Edildi
+
+| Kısa İsim  | Açıklama                                                                                             |
+|------------|------------------------------------------------------------------------------------------------------|
+| Baseline   | Bir iş ilanı verin ve bir mezun için uygun olup olmadığını sorun.                                    |
+| CoT        | Sorgulamadan önce birkaç doğru sınıflandırma örneği verin.                                           |
+| Zero-CoT   | Cevabını vermeden önce modelden adım adım akıl yürütmesini isteyin.                                  |
+| rawinst    | Kullanıcı mesajına ekleyerek rolü ve görevi hakkında talimatlar verin.                               |
+| sysinst    | Bir sistem mesajı olarak rolü ve görevi hakkında talimatlar verin.                                   |
+| bothinst   | Bir sistem mesajı olarak role ve bir kullanıcı mesajı olarak göreve sahip yönergeler bölünmüştür .   |
+| mock       | Bir tartışmayı kabul ettiği yerde alay ederek görev yönergeleri verin.                               |
+| reit       | Talimatlardaki temel unsurları tekrarlayarak güçlendirin.                                            |
+| strict     | Modelden belirli bir şablonu kesinlikle takip ederek yanıt vermesini isteyin.                        |
+| loose      | Belirli bir şablona göre verilecek nihai cevabı isteyin.                                             |
+| right      | Modelden doğru sonuca varmasını isteyin.                                                             |
+| info       | Yaygın muhakeme hatalarını ele almak için ek bilgiler sağlayın.                                      |
+| name       | Modele, konuşmada atıfta bulunduğumuz bir isim verin.                                                |
+| pos        | Modeli sorgulamadan önce olumlu geri bildirim sağlayın.                                              |
+
+
+### Tüm Bilgi İstemi Değişikliklerinin Performans Etkisi
+
+|                                        | Precision     | Recall        | F1            | Template Stickiness    |
+|----------------------------------------|---------------|---------------|---------------|------------------------|
+| _Baseline_                             | _61.2_        | _70.6_        | _65.6_        | _79%_                  |
+| _CoT_                                  | _72.6_        | _85.1_        | _78.4_        | _87%_                  |
+| _Zero-CoT_                             | _75.5_        | _88.3_        | _81.4_        | _65%_                  |
+| _+rawinst_                             | _80_          | _92.4_        | _85.8_        | _68%_                  |
+| _+sysinst_                             | _77.7_        | _90.9_        | _83.8_        | _69%_                  |
+| _+bothinst_                            | _81.9_        | _93.9_        | _87.5_        | _71%_                  |
+| +bothinst+mock                         | 83.3          | 95.1          | 88.8          | 74%                    |
+| +bothinst+mock+reit                    | 83.8          | 95.5          | 89.3          | 75%                    |
+| _+bothinst+mock+reit+strict_           | _79.9_        | _93.7_        | _86.3_        | _**98%**_              |
+| _+bothinst+mock+reit+loose_            | _80.5_        | _94.8_        | _87.1_        | _95%_                  |
+| +bothinst+mock+reit+right              | 84            | 95.9          | 89.6          | 77%                    |
+| +bothinst+mock+reit+right+info         | 84.9          | 96.5          | 90.3          | 77%                    |
+| +bothinst+mock+reit+right+info+name    | 85.7          | 96.8          | 90.9          | 79%                    |
+| +bothinst+mock+reit+right+info+name+pos| **86.9**      | **97**        | **91.7**      | 81%                    |
+
+Şablon yapışkanlığı, modelin istenen biçimde ne sıklıkta yanıt verdiğini ifade eder.
+
diff --git a/pages/course.tr.mdx b/pages/course.tr.mdx
new file mode 100644
index 0000000..7d206e0
--- /dev/null
+++ b/pages/course.tr.mdx
@@ -0,0 +1,9 @@
+# Hızlı Mühendislik Kursu
+
+Mayıs 2023'te bir ["LLM'ler için Prompting Engineering"](https://www.getsphere.com/cohorts/prompt-engineering-for-llms?source=promptingguide) kursu vermek üzere Sphere ile ortaklık kurduk.
+
+Bu uygulamalı kurs, en iyi büyük dil modellerinin uygulamalarını etkin bir şekilde oluşturmak için gerçek dünyada kullanılan en son hızlı mühendislik tekniklerini ve araçlarını öğretmek için tasarlanmıştır.
+
+Hızlı mühendislik becerilerinizi bir sonraki seviyeye taşımak istiyorsanız, kursu şiddetle tavsiye ederiz.
+
+Bu kurs ayrıca bir bitirme sertifikası içerir.
\ No newline at end of file
diff --git a/pages/datasets.tr.mdx b/pages/datasets.tr.mdx
new file mode 100644
index 0000000..395fb5a
--- /dev/null
+++ b/pages/datasets.tr.mdx
@@ -0,0 +1,12 @@
+# Veri setleri
+#### (İsme göre sıralandı)
+
+- [Anthropic's Red Team dataset](https://github.com/anthropics/hh-rlhf/tree/master/red-team-attempts), [(paper)](https://arxiv.org/abs/2209.07858)
+- [Awesome ChatGPT Prompts](https://huggingface.co/datasets/fka/awesome-chatgpt-prompts)
+- [DiffusionDB](https://github.com/poloclub/diffusiondb)
+- [Midjourney Prompts](https://huggingface.co/datasets/succinctly/midjourney-prompts)
+- [P3 - Public Pool of Prompts](https://huggingface.co/datasets/bigscience/P3)
+- [PartiPrompts](https://parti.research.google)
+- [Real Toxicity Prompts](https://allenai.org/data/real-toxicity-prompts)
+- [Stable Diffusion Dataset](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts)
+- [WritingPrompts](https://www.reddit.com/r/WritingPrompts)
diff --git a/pages/index.tr.mdx b/pages/index.tr.mdx
new file mode 100644
index 0000000..1407387
--- /dev/null
+++ b/pages/index.tr.mdx
@@ -0,0 +1,9 @@
+# Hızlı Mühendislik Kılavuzu
+
+İstem mühendisliği, çok çeşitli uygulamalar ve araştırma konuları için dil modellerini (LM'ler) verimli bir şekilde kullanmak üzere bilgi istemleri geliştirmek ve optimize etmek için nispeten yeni bir disiplindir. Hızlı mühendislik becerileri, büyük dil modellerinin (LLM'ler) yeteneklerini ve sınırlamalarını daha iyi anlamaya yardımcı olur.
+
+Araştırmacılar, soru cevaplama ve aritmetik muhakeme gibi çok çeşitli ortak ve karmaşık görevlerde LLM'lerin kapasitesini geliştirmek için hızlı mühendisliği kullanır. Geliştiriciler, LLM'ler ve diğer araçlarla arabirim oluşturan sağlam ve etkili yönlendirme teknikleri tasarlamak için istem mühendisliğini kullanır.
+
+Bilgi istemi mühendisliği yalnızca bilgi istemlerini tasarlamak ve geliştirmekle ilgili değildir. LLM'lerle etkileşim kurmak ve gelişmek için yararlı olan çok çeşitli becerileri ve teknikleri kapsar. LLM'lerin yeteneklerini arabirim oluşturmak, bunlarla oluşturmak ve anlamak önemli bir beceridir. LLM'lerin güvenliğini artırmak ve LLM'leri alan bilgisi ve harici araçlarla zenginleştirmek gibi yeni yetenekler oluşturmak için hızlı mühendisliği kullanabilirsiniz.
+
+LLM'lerle geliştirme konusundaki yüksek ilgiden motive olarak, en son makaleleri, öğrenme kılavuzlarını, modelleri, dersleri, referansları, yeni LLM yeteneklerini ve hızlı mühendislikle ilgili araçları içeren bu yeni hızlı mühendislik kılavuzunu oluşturduk.
\ No newline at end of file
diff --git a/pages/introduction.tr.mdx b/pages/introduction.tr.mdx
new file mode 100644
index 0000000..f3146e9
--- /dev/null
+++ b/pages/introduction.tr.mdx
@@ -0,0 +1,7 @@
+# Giriş
+
+İstem mühendisliği, çok çeşitli uygulamalar ve araştırma konuları için dil modellerini (LM'ler) verimli bir şekilde kullanmak üzere bilgi istemleri geliştirmek ve optimize etmek için nispeten yeni bir disiplindir. Hızlı mühendislik becerileri, büyük dil modellerinin (LLM'ler) yeteneklerini ve sınırlamalarını daha iyi anlamaya yardımcı olur. Araştırmacılar, soru cevaplama ve aritmetik muhakeme gibi çok çeşitli ortak ve karmaşık görevlerde LLM'lerin kapasitesini geliştirmek için hızlı mühendisliği kullanır. Geliştiriciler, LLM'ler ve diğer araçlarla arabirim oluşturan sağlam ve etkili yönlendirme teknikleri tasarlamak için istem mühendisliğini kullanır.
+
+Bu kılavuz, büyük dil modelleriyle (LLM'ler) etkileşimde bulunmak ve talimat vermek için bilgi istemlerinin nasıl kullanılacağına dair kabaca bir fikir sağlamak için bilgi istemlerinin temellerini kapsar.
+
+Tüm örnekler, aksi belirtilmedikçe `text-davinci-003` (OpenAI'nin oyun alanı kullanılarak) ile test edilmiştir. Varsayılan konfigürasyonları kullanır, yani "sıcaklık=0,7" ve "top-p=1".
\ No newline at end of file
diff --git a/pages/introduction/_meta.tr.json b/pages/introduction/_meta.tr.json
new file mode 100644
index 0000000..52372db
--- /dev/null
+++ b/pages/introduction/_meta.tr.json
@@ -0,0 +1,8 @@
+{
+    "settings": "LLM Settings",
+    "basics": "Basics of Prompting",
+    "elements": "Prompt Elements",
+    "tips": "General Tips for Designing Prompts",
+    "examples": "Examples of Prompts"
+}
+  
\ No newline at end of file
diff --git a/pages/introduction/basics.tr.mdx b/pages/introduction/basics.tr.mdx
new file mode 100644
index 0000000..b88aa54
--- /dev/null
+++ b/pages/introduction/basics.tr.mdx
@@ -0,0 +1,114 @@
+# Bilgi İstemcisinin Temelleri
+
+## Temel İstemler
+
+Basit istemlerle çok şey başarabilirsiniz, ancak sonuçların kalitesi, ona ne kadar bilgi verdiğinize ve ne kadar iyi hazırlanmış olduğuna bağlıdır. Bilgi istemi, modele ilettiğiniz *talimat* veya *soru* gibi bilgileri ve *bağlam*, *girdiler* veya *örnekler* gibi diğer ayrıntıları içerebilir. Modeli daha iyi yönlendirmek ve sonuç olarak daha iyi sonuçlar almak için bu öğeleri kullanabilirsiniz.
+
+Basit bir bilgi isteminin temel bir örneğini gözden geçirerek başlayalım:
+
+*Bilgi İstemcisi*
+```
+Gökyüzü
+```
+
+*Çıktı:*
+```
+mavi
+
+Açık bir günde gökyüzü mavidir. Bulutlu bir günde gökyüzü gri veya beyaz olabilir.
+```
+
+Gördüğünüz gibi, dil modeli, `"Gökyüzü"' bağlamı göz önüne alındığında anlamlı olan dizelerin bir devamını çıkarır. Çıktı beklenmedik olabilir veya başarmak istediğimiz görevden uzak olabilir. 
+
+Bu temel örnek, özellikle neyi başarmak istediğimize dair daha fazla bağlam veya talimat sağlama gerekliliğini de vurgulamaktadır.
+
+Biraz geliştirmeye çalışalım:
+
+*Bilgi İstemcisi:*
+```
+Cümleyi tamamla: 
+
+Gökyüzü
+```
+
+*Çıktı:*
+
+```
+çok güzel bugün.
+```
+
+Bu daha mı iyi? Pekala, modele cümleyi tamamlamasını söyledik, böylece sonuç tam olarak yapmasını söylediğimiz şeyi takip ettiği için ("cümleyi tamamlayın") çok daha iyi görünüyor. Modele bir görevi gerçekleştirme talimatı vermek için en uygun bilgi istemlerini tasarlamaya yönelik bu yaklaşım, **hızlı mühendislik** olarak adlandırılır.
+
+Yukarıdaki örnek, bugün LLM'lerle neyin mümkün olduğunun temel bir örneğidir. Günümüzün LLM'leri, metin özetlemeden matematiksel akıl yürütmeye ve kod oluşturmaya kadar her türlü gelişmiş görevi gerçekleştirebilir.
+
+## Bilgi İstemcisi Formatı
+
+Yukarıda çok basit bir komut istemi denedik. Standart bir bilgi istemi aşağıdaki biçime sahiptir:
+
+```
+<Soru>?
+```
+
+ya da  
+
+```
+<Talimat>
+```
+ 
+Bu, birçok SoruCevap veri kümesinde standart olan bir soru yanıtlama (QA) biçimine şu şekilde biçimlendirilebilir:
+
+```
+S: <Soru>?
+C: 
+```
+
+Yukarıdaki gibi istemde bulunurken, aynı zamanda *sıfır vuruşlu istem* olarak da adlandırılır, yani, gerçekleştirmesini istediğiniz görevle ilgili herhangi bir örnek veya gösteri olmadan doğrudan modelden bir yanıt istemiş olursunuz. Bazı büyük dil modelleri, sıfır vuruşlu yönlendirme gerçekleştirme yeteneğine sahiptir, ancak bu, eldeki görevin karmaşıklığına ve bilgisine bağlıdır.
+
+Yukarıdaki standart biçim göz önüne alındığında, popüler ve etkili bir yönlendirme tekniği, örnekler (örn. gösteriler) sağladığımız durumlarda *few-shot prompting* olarak anılır. Few-shot prompts aşağıdaki şekilde gösterilebilir:
+
+```
+<Soru>?
+<Cevap>
+
+<Soru>?
+<Cevavp>
+
+<Soru>?
+<Cevap>
+
+<Soru>?
+
+```
+
+Soru Cevap sürümü şuna benzer:
+
+```
+S: <Soru>?
+C: <Cevap>
+
+S: <Soru>?
+C: <Cevap>
+
+S: <Soru>?
+C: <Cevap>
+
+S: <Soru>?
+C:
+```
+
+Soru cevap formatını kullanmanın gerekli olmadığını unutmayın. Bilgi istemi biçimi eldeki göreve bağlıdır. Örneğin, basit bir sınıflandırma görevi gerçekleştirebilir ve aşağıdaki gibi görevi gösteren örnekler verebilirsiniz:
+
+*Bilgi İstemcisi:*
+```
+Bu harika! // Olumlu
+Bu kötü! // Olumsuz
+Vay canına o film harikaydı! // Olumlu
+Ne kadar kötü bir film// Olumsuz
+```
+
+*Çıktı:*
+```
+Olumsuz
+```
+
+Few-shotbilgi istemleri, dil modellerinin birkaç gösterim verilen görevleri öğrenme yeteneği olan bağlam içi öğrenmeyi etkinleştirir.
diff --git a/pages/introduction/elements.tr.mdx b/pages/introduction/elements.tr.mdx
new file mode 100644
index 0000000..3c7698d
--- /dev/null
+++ b/pages/introduction/elements.tr.mdx
@@ -0,0 +1,15 @@
+# Bilgi İstemin Öğeleri
+
+Hızlı mühendislikle mümkün olan daha fazla örneği ve uygulamayı ele aldıkça, istemi oluşturan belirli unsurların olduğunu fark edeceksiniz.
+
+Bir bilgi istemi aşağıdaki bileşenlerden herhangi birini içerebilir:
+
+**Talimat** - modelin gerçekleştirmesini istediğiniz belirli bir görev veya talimat
+
+**Bağlam** - modeli daha iyi yanıtlara yönlendirebilecek harici bilgileri veya ek bağlamı içerebilir
+
+**Girdi Verileri** - yanıtını bulmak istediğimiz girdi veya sorudur
+
+**Çıktı Göstergesi** - çıktının türünü veya formatını gösterir.
+
+Bir bilgi istemi için tüm bileşenler gerekli değildir ve biçim eldeki göreve bağlıdır. Gelecek rehberlerde daha somut örneklere değineceğiz.
\ No newline at end of file
diff --git a/pages/introduction/examples.tr.mdx b/pages/introduction/examples.tr.mdx
new file mode 100644
index 0000000..e6d3a60
--- /dev/null
+++ b/pages/introduction/examples.tr.mdx
@@ -0,0 +1,3 @@
+# Examples of Prompts
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/introduction/settings.tr.mdx b/pages/introduction/settings.tr.mdx
new file mode 100644
index 0000000..e7dec7c
--- /dev/null
+++ b/pages/introduction/settings.tr.mdx
@@ -0,0 +1,11 @@
+# LLM Ayarları
+
+Bilgi istemleriyle çalışırken, LLM ile bir API aracılığıyla veya doğrudan etkileşim kuracaksınız. İstemleriniz için farklı sonuçlar almak üzere birkaç parametreyi yapılandırabilirsiniz.
+
+**Sıcaklık** - Kısacası, "sıcaklık" ne kadar düşük olursa, her zaman bir sonraki olası en yüksek jetonun seçilmesi anlamında sonuçlar o kadar belirleyici olur. Artan sıcaklık, daha çeşitli veya yaratıcı çıktıları teşvik eden daha fazla rastgeleliğe yol açabilir. Esasen diğer olası belirteçlerin ağırlıklarını artırıyoruz. Uygulama açısından, daha olgusal ve özlü yanıtları teşvik etmek için gerçeğe dayalı soru cevap gibi görevler için daha düşük bir sıcaklık değeri kullanmak isteyebiliriz. Şiir oluşturma veya diğer yaratıcı görevler için sıcaklık değerini artırmak faydalı olabilir.
+
+**Top_p** - Benzer şekilde, çekirdek örnekleme adı verilen sıcaklığa sahip bir örnekleme tekniği olan "top_p" ile, modelin yanıt oluşturmada ne kadar belirleyici olduğunu kontrol edebilirsiniz. Kesin ve gerçek cevaplar arıyorsanız, bunu düşük tutun. Daha çeşitli yanıtlar arıyorsanız, daha yüksek bir değere yükseltin.
+
+Genel tavsiye, ikisini birden değil, birini değiştirmektir.
+
+Bazı temel örneklerle başlamadan önce, sonuçlarınızın kullandığınız LLM sürümüne bağlı olarak değişebileceğini unutmayın.
\ No newline at end of file
diff --git a/pages/introduction/tips.tr.mdx b/pages/introduction/tips.tr.mdx
new file mode 100644
index 0000000..2086993
--- /dev/null
+++ b/pages/introduction/tips.tr.mdx
@@ -0,0 +1,3 @@
+# General Tips for Designing Prompts
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/models.tr.mdx b/pages/models.tr.mdx
new file mode 100644
index 0000000..2e0638c
--- /dev/null
+++ b/pages/models.tr.mdx
@@ -0,0 +1,9 @@
+# Modeller
+
+import { Callout } from 'nextra-theme-docs'
+
+Bu bölümde, en yeni dil modellerinden bazılarını ve bunların en yeni ve en gelişmiş yönlendirme mühendisliği tekniklerini nasıl başarıyla uyguladıklarını ele alacağız. Ek olarak, bu modellerin bir dizi görevdeki yeteneklerini ve az atışlı yönlendirme, sıfır atışlı yönlendirme ve düşünce zinciri yönlendirmesi gibi komut istemi kurulumlarını ele alıyoruz. Bu yetenekleri anlamak, bu modellerin sınırlamalarını ve bunların nasıl etkili bir şekilde kullanılacağını anlamak için önemlidir.
+
+<Callout emoji="⚠️">
+  Bu bölüm yoğun geliştirme aşamasındadır.
+</Callout>
\ No newline at end of file
diff --git a/pages/models/_meta.tr.json b/pages/models/_meta.tr.json
new file mode 100644
index 0000000..a449f46
--- /dev/null
+++ b/pages/models/_meta.tr.json
@@ -0,0 +1,8 @@
+{
+    "flan": "Flan",
+    "chatgpt": "ChatGPT",
+    "llama": "LLaMA",
+    "gpt-4": "GPT-4",
+    "collection": "Model Collection" 
+}
+  
\ No newline at end of file
diff --git a/pages/models/collection.tr.mdx b/pages/models/collection.tr.mdx
new file mode 100644
index 0000000..9da60ae
--- /dev/null
+++ b/pages/models/collection.tr.mdx
@@ -0,0 +1,65 @@
+# Model Koleksiyonu
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+
+<Callout emoji="⚠️">
+  Bu bölüm yoğun geliştirme aşamasındadır.
+</Callout>
+
+Bu bölüm, dikkate değer ve temel LLM'lerin bir koleksiyonunu ve özetini içerir. (Veriler [Papers with Code](https://paperswithcode.com/methods/category/language-models) ve [Zhao ve diğerleri (2023)] tarafından yapılan son çalışmadan alınmıştır.(https://arxiv.org/pdf/2303.18223.pdf).
+
+
+## Modeller
+
+| Model | Çıkış Tarihi | Açıklama | 
+| --- | --- | --- | 
+| [BERT](https://arxiv.org/abs/1810.04805)| 2018 | Bidirectional Encoder Representations from Transformers | 
+| [GPT](https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/language-unsupervised/language_understanding_paper.pdf) | 2018 | Improving Language Understanding by Generative Pre-Training | 
+| [RoBERTa](https://arxiv.org/abs/1907.11692) | 2019 | A Robustly Optimized BERT Pretraining Approach | 
+| [GPT-2](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) | 2019 | Language Models are Unsupervised Multitask Learners | 
+| [T5](https://arxiv.org/abs/1910.10683) | 2019 | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | 
+| [BART](https://arxiv.org/abs/1910.13461) | 2019 | Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |
+| [ALBERT](https://arxiv.org/abs/1909.11942) |2019 | A Lite BERT for Self-supervised Learning of Language Representations | 
+| [XLNet](https://arxiv.org/abs/1906.08237) | 2019 | Generalized Autoregressive Pretraining for Language Understanding and Generation |
+| [CTRL](https://arxiv.org/abs/1909.05858) |2019 | CTRL: A Conditional Transformer Language Model for Controllable Generation | 
+| [ERNIE](https://arxiv.org/abs/1904.09223v1) | 2019| ERNIE: Enhanced Representation through Knowledge Integration |
+| [GShard](https://arxiv.org/abs/2006.16668v1) | 2020 | GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding |
+| [GPT-3](https://arxiv.org/abs/2005.14165) | 2020 | Language Models are Few-Shot Learners |
+| [LaMDA](https://arxiv.org/abs/2201.08239v3) | 2021 | LaMDA: Language Models for Dialog Applications | 
+| [PanGu-α](https://arxiv.org/abs/2104.12369v1) | 2021 | PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation |
+| [mT5](https://arxiv.org/abs/2010.11934v3) | 2021 | mT5: A massively multilingual pre-trained text-to-text transformer |
+| [CPM-2](https://arxiv.org/abs/2106.10715v3) | 2021 | CPM-2: Large-scale Cost-effective Pre-trained Language Models |
+| [T0](https://arxiv.org/abs/2110.08207) |2021 |Multitask Prompted Training Enables Zero-Shot Task Generalization |
+| [HyperCLOVA](https://arxiv.org/abs/2109.04650) | 2021 | What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers |
+| [Codex](https://arxiv.org/abs/2107.03374v2) |2021 |Evaluating Large Language Models Trained on Code |
+| [ERNIE 3.0](https://arxiv.org/abs/2107.02137v1) | 2021 | ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation|
+| [Jurassic-1](https://uploads-ssl.webflow.com/60fd4503684b466578c0d307/61138924626a6981ee09caf6_jurassic_tech_paper.pdf) | 2021 | Jurassic-1: Technical Details and Evaluation |
+| [FLAN](https://arxiv.org/abs/2109.01652v5) | 2021 | Finetuned Language Models Are Zero-Shot Learners |
+| [MT-NLG](https://arxiv.org/abs/2201.11990v3) | 2021 | Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model|
+| [Yuan 1.0](https://arxiv.org/abs/2110.04725v2) | 2021| Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning |
+| [WebGPT](https://arxiv.org/abs/2112.09332v3) | 2021 | WebGPT: Browser-assisted question-answering with human feedback |
+| [Gopher](https://arxiv.org/abs/2112.11446v2) |2021 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
+| [ERNIE 3.0 Titan](https://arxiv.org/abs/2112.12731v1) |2021 | ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation |
+| [GLaM](https://arxiv.org/abs/2112.06905) | 2021 | GLaM: Efficient Scaling of Language Models with Mixture-of-Experts |
+| [InstructGPT](https://arxiv.org/abs/2203.02155v1) | 2022 | Training language models to follow instructions with human feedback |
+| [GPT-NeoX-20B](https://arxiv.org/abs/2204.06745v1) | 2022 | GPT-NeoX-20B: An Open-Source Autoregressive Language Model |
+| [AlphaCode](https://arxiv.org/abs/2203.07814v1) | 2022 | Competition-Level Code Generation with AlphaCode |
+| [CodeGen](https://arxiv.org/abs/2203.13474v5) | 2022 | CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis |
+| [Chinchilla](https://arxiv.org/abs/2203.15556) | 2022 | Shows that for a compute budget, the best performances are not achieved by the largest models but by smaller models trained on more data. |
+| [Tk-Instruct](https://arxiv.org/abs/2204.07705v3) | 2022 | Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks |
+| [UL2](https://arxiv.org/abs/2205.05131v3) | 2022 | UL2: Unifying Language Learning Paradigms |
+| [PaLM](https://arxiv.org/abs/2204.02311v5) |2022| PaLM: Scaling Language Modeling with Pathways |
+| [OPT](https://arxiv.org/abs/2205.01068) | 2022 | OPT: Open Pre-trained Transformer Language Models |
+| [BLOOM](https://arxiv.org/abs/2211.05100v3) | 2022 | BLOOM: A 176B-Parameter Open-Access Multilingual Language Model |
+| [GLM-130B](https://arxiv.org/abs/2210.02414v1) | 2022 | GLM-130B: An Open Bilingual Pre-trained Model |
+| [AlexaTM](https://arxiv.org/abs/2208.01448v2) | 2022 | AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model |
+| [Flan-T5](https://arxiv.org/abs/2210.11416v5) | 2022 | Scaling Instruction-Finetuned Language Models |
+| [Sparrow](https://arxiv.org/abs/2209.14375) | 2022 | Improving alignment of dialogue agents via targeted human judgements |
+| [U-PaLM](https://arxiv.org/abs/2210.11399v2) | 2022 | Transcending Scaling Laws with 0.1% Extra Compute |
+| [mT0](https://arxiv.org/abs/2211.01786v1) | 2022 | Crosslingual Generalization through Multitask Finetuning |
+| [Galactica](https://arxiv.org/abs/2211.09085v1) | 2022 | Galactica: A Large Language Model for Science |
+| [OPT-IML](https://arxiv.org/abs/2212.12017v3) | 2022 | OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization |
+| [LLaMA](https://arxiv.org/abs/2302.13971v1) | 2023 | LLaMA: Open and Efficient Foundation Language Models |
+| [GPT-4](https://arxiv.org/abs/2303.08774v3) | 2023 |GPT-4 Technical Report |
+| [PanGu-Σ](https://arxiv.org/abs/2303.10845v1) | 2023 | PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing |
+| [BloombergGPT](https://arxiv.org/abs/2303.17564v1)| 2023 |BloombergGPT: A Large Language Model for Finance|
\ No newline at end of file
diff --git a/pages/models/flan.tr.mdx b/pages/models/flan.tr.mdx
new file mode 100644
index 0000000..3d42316
--- /dev/null
+++ b/pages/models/flan.tr.mdx
@@ -0,0 +1,3 @@
+# Scaling Instruction-Finetuned Language Models
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/models/gpt-4.tr.mdx b/pages/models/gpt-4.tr.mdx
new file mode 100644
index 0000000..2d6f4e4
--- /dev/null
+++ b/pages/models/gpt-4.tr.mdx
@@ -0,0 +1,3 @@
+# GPT-4 
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/models/llama.tr.mdx b/pages/models/llama.tr.mdx
new file mode 100644
index 0000000..11624b0
--- /dev/null
+++ b/pages/models/llama.tr.mdx
@@ -0,0 +1,43 @@
+## LLaMA: Açık ve Verimli Temel Dil Modelleri
+
+<Callout emoji="⚠️">
+ Bu bölüm yoğun geliştirme aşamasındadır.
+</Callout>
+
+
+import {Screenshot} from 'components/screenshot'
+import { Callout, FileTree } from 'nextra-theme-docs'
+import LLAMA1 from '../../img/llama-1.png'
+
+
+## Yenilikler Neler?
+
+Bu makale, 7B ila 65B parametreleri arasında değişen temel dil modelleri koleksiyonunu tanıtmaktadır.
+
+Modeller, halka açık veri kümeleriyle trilyonlarca jeton üzerinde eğitilmiştir.
+
+[(Hoffman ve diğerleri 2022)](https://arxiv.org/abs/2203.15556) tarafından yapılan çalışma, çok daha fazla veriyle eğitilen daha küçük modellerin, daha büyük benzerlerine göre daha iyi performans elde edebildiğini göstermektedir.Bu çalışma, 10B modellerinin 200B belirteçleri üzerinde eğitilmesini önerir. Bununla birlikte, LLaMA makalesi, bir 7B modelinin performansının 1T belirteçlerinden sonra bile gelişmeye devam ettiğini ortaya koymaktadır.
+
+<Screenshot src={LLAMA1} alt="LLAMA1" />
+
+Bu çalışma, daha fazla belirteç üzerinde eğitim alarak çeşitli çıkarım bütçelerinde mümkün olan en iyi performansı elde eden eğitim modellerine (LLaMA) odaklanmaktadır.
+
+
+## Yetenekler ve Önemli Sonuçlar
+
+Genel olarak LLaMA-13B, 10 kat daha küçük olmasına ve tek bir GPU çalıştırmanın mümkün olmasına rağmen birçok karşılaştırmada GPT-3(175B)'den daha iyi performans gösteriyor. LLaMA 65B, Chinchilla-70B ve PaLM-540B gibi modellerle rekabet halindedir.
+
+
+*Makale:* [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
+
+*Kod:* https://github.com/facebookresearch/llama
+
+## Referanslar
+
+- [Koala: A Dialogue Model for Academic Research](https://bair.berkeley.edu/blog/2023/04/03/koala/) (April 2023)
+- [Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data](https://arxiv.org/abs/2304.01196) (April 2023)
+- [Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality](https://vicuna.lmsys.org/) (March 2023)
+- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://arxiv.org/abs/2303.16199) (March 2023)
+- [GPT4All](https://github.com/nomic-ai/gpt4all) (March 2023)
+- [ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge](https://arxiv.org/abs/2303.14070) (March 2023)
+- [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) (March 2023)
\ No newline at end of file
diff --git a/pages/notebooks.tr.mdx b/pages/notebooks.tr.mdx
new file mode 100644
index 0000000..a413bb9
--- /dev/null
+++ b/pages/notebooks.tr.mdx
@@ -0,0 +1,11 @@
+# Prompt Mühendislik Not Defterleri
+
+Hızlı mühendisliğe başlamanıza yardımcı olmak için tasarladığımız bir not defteri koleksiyonu içerir. Yakında eklenecek daha fazlası!
+
+| Açıklama   | Not Defterleri   | 
+| :------------ | :---------: | 
+|Learn how to perform many different types of common tasks using the `openai` and `LangChain` library|[Getting Started with Prompt Engineering](https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/notebooks/pe-lecture.ipynb)|
+|Learn how to use code as reasoning for solving common tasks using the Python interpreter in combination with the language model.|[Program-Aided Language Model](https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/notebooks/pe-pal.ipynb)|
+|Learn more about how to make calls to the ChatGPT APIs using the `openai` library.|[ChatGPT API Intro](https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/notebooks/pe-chatgpt-intro.ipynb)|
+|Learn how to use ChatGPT features using the `LangChain` library. |[ChatGPT API with LangChain](https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/notebooks/pe-chatgpt-langchain.ipynb)|
+|Learn about adversarial prompting include defensive measures.|[Adversarial Prompt Engineering](https://github.com/dair-ai/Prompt-Engineering-Guide/blob/main/notebooks/pe-chatgpt-adversarial.ipynb)|
diff --git a/pages/papers.tr.mdx b/pages/papers.tr.mdx
new file mode 100644
index 0000000..143421c
--- /dev/null
+++ b/pages/papers.tr.mdx
@@ -0,0 +1,174 @@
+# Makaleler
+
+Aşağıdakiler, hızlı mühendislikle ilgili en son makalelerdir (yayınlanma tarihine göre sıralanmıştır). Bunu günlük olarak güncelliyoruz ve yeni makaleler geliyor. Bu makalelerin özetlerini her hafta yukarıdaki kılavuzlara dahil ediyoruz.
+
+## Genel Bakış
+
+  - [Nature Language Reasoning, A Survey](https://arxiv.org/abs/2303.14725) (March 2023)
+  - [Augmented Language Models: a Survey](https://arxiv.org/abs/2302.07842) (Feb 2023)
+  - [A Survey for In-context Learning](https://arxiv.org/abs/2301.00234) (Dec 2022)
+  - [Towards Reasoning in Large Language Models: A Survey](https://arxiv.org/abs/2212.10403) (Dec 2022)
+  - [Reasoning with Language Model Prompting: A Survey](https://arxiv.org/abs/2212.09597) (Dec 2022)
+  - [Emergent Abilities of Large Language Models](https://arxiv.org/abs/2206.07682) (Jun 2022)
+  - [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://arxiv.org/abs/2204.13988) (Apr 2022)
+  - [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://arxiv.org/abs/2107.13586) (Jul 2021)
+
+## Yaklaşımlar
+  
+  - [Self-Refine: Iterative Refinement with Self-Feedback](https://arxiv.org/abs/2303.17651v1) (Mar 2023)
+  - [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://arxiv.org/abs/2303.13824) (Mar 2023)
+  - [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://arxiv.org/abs/2303.13283) (Mar 2023)
+  - [Fairness-guided Few-shot Prompting for Large Language Models](https://arxiv.org/abs/2303.13217) (Mar 2023)
+  - [Context-faithful Prompting for Large Language Models](https://arxiv.org/abs/2303.11315) (Mar 2023)
+  - [Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning](https://arxiv.org/abs/2303.10475) (Mar 2023)
+  - [UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation](https://arxiv.org/abs/2303.08518) (Mar 2023)
+  - [Model-tuning Via Prompts Makes NLP Models Adversarially Robust](https://arxiv.org/abs/2303.07320) (Mar 2023)
+  - [Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer](https://arxiv.org/abs/2303.03922) (March 2023)
+  - [CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification](https://arxiv.org/abs/2303.03628) (March 2023)
+  - [Larger language models do in-context learning differently](https://arxiv.org/abs/2303.03846) (March 2023)
+  - [OpenICL: An Open-Source Framework for In-context Learning](https://arxiv.org/abs/2303.02913) (March 2023)
+  - [Dynamic Prompting: A Unified Framework for Prompt Tuning](https://arxiv.org/abs/2303.02909) (March 2023)
+  - [Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning](https://arxiv.org/abs/2303.02861) (March 2023)
+  - [Effectiveness of Data Augmentation for Prefix Tuning with Limited Data](https://arxiv.org/abs/2303.02577) (March 2023)
+  - [Mixture of Soft Prompts for Controllable Data Generation](https://arxiv.org/abs/2303.01580) (March 2023)
+  - [Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners](https://arxiv.org/abs/2303.02151) (March 2023)
+  - [How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks](https://arxiv.org/abs/2303.00293) (March 2023)
+  - [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://arxiv.org/pdf/2302.10198.pdf) (Feb 2023)
+  - [EvoPrompting: Language Models for Code-Level Neural Architecture Search](https://arxiv.org/abs/2302.14838) (Feb 2023)
+  - [In-Context Instruction Learning](https://arxiv.org/abs/2302.14691) (Feb 2023)
+  - [Chain of Hindsight Aligns Language Models with Feedback](https://arxiv.org/abs/2302.02676) (Feb 2023)
+  - [Language Is Not All You Need: Aligning Perception with Language Models](https://arxiv.org/abs/2302.14045) (Feb 2023)
+  - [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://arxiv.org/abs/2302.12822) (Feb 2023)
+  - [Active Prompting with Chain-of-Thought for Large Language Models](https://arxiv.org/abs/2302.12246) (Feb 2023)
+  - [More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models](https://arxiv.org/abs/2302.12173) (Feb 2023)
+  - [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://arxiv.org/abs/2302.11382) (Feb 2023)
+  - [Guiding Large Language Models via Directional Stimulus Prompting](https://arxiv.org/abs/2302.11520) (Feb 2023)
+  - [How Does In-Context Learning Help Prompt Tuning?](https://arxiv.org/abs/2302.11521) (Feb 2023)
+  - [Scalable Prompt Generation for Semi-supervised Learning with Language Models](https://arxiv.org/abs/2302.09236) (Feb 2023)
+  - [Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints](https://arxiv.org/abs/2302.09185) (Feb 2023)
+  - [À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting](https://arxiv.org/abs/2302.07994) (Feb 2023)
+  - [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://arxiv.org/abs/2302.08043) (Feb 2023)
+  - [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
+  - [SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains](https://arxiv.org/abs/2302.06868) (Feb 2023)
+  - [Evaluating the Robustness of Discrete Prompts](https://arxiv.org/abs/2302.05619) (Feb 2023)
+  - [Compositional Exemplars for In-context Learning](https://arxiv.org/abs/2302.05698) (Feb 2023)
+  - [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://arxiv.org/abs/2302.03668) (Feb 2023)
+  - [Multimodal Chain-of-Thought Reasoning in Language Models](https://arxiv.org/abs/2302.00923) (Feb 2023)
+  - [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://arxiv.org/abs/2302.00093) (Feb 2023)
+  - [Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models](https://arxiv.org/abs/2302.00618) (Feb 2023)
+  - [Progressive Prompts: Continual Learning for Language Models](https://arxiv.org/abs/2301.12314) (Jan 2023)
+  - [Batch Prompting: Efficient Inference with LLM APIs](https://arxiv.org/abs/2301.08721) (Jan 2023)
+  - [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://arxiv.org/abs/2212.14024) (Dec 2022)
+  - [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://arxiv.org/abs/2212.08061) (Dec 2022)
+  - [Constitutional AI: Harmlessness from AI Feedback](https://arxiv.org/abs/2212.08073) (Dec 2022)
+  - [Successive Prompting for Decomposing Complex Questions](https://arxiv.org/abs/2212.04092) (Dec 2022)
+  - [Large Language Models are reasoners with Self-Verification](https://arxiv.org/abs/2212.09561v1) (Dec 2022)
+  - [Discovering Language Model Behaviors with Model-Written Evaluations](https://arxiv.org/abs/2212.09251) (Dec 2022)
+  - [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://arxiv.org/abs/2212.06713) (Dec 2022)
+  - [PAL: Program-aided Language Models](https://arxiv.org/abs/2211.10435) (Nov 2022)
+  - [Large Language Models Are Human-Level Prompt Engineers](https://arxiv.org/abs/2211.01910) (Nov 2022)
+  - [Ignore Previous Prompt: Attack Techniques For Language Models](https://arxiv.org/abs/2211.09527) (Nov 2022)
+  - [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://arxiv.org/abs/2210.07321) (Nov 2022)
+  - [Teaching Algorithmic Reasoning via In-context Learning](https://arxiv.org/abs/2211.09066) (Nov 2022)
+  - [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://arxiv.org/abs/2211.11875) (Nov 2022)
+  - [Ask Me Anything: A simple strategy for prompting language models](https://paperswithcode.com/paper/ask-me-anything-a-simple-strategy-for) (Oct 2022)
+  - [Recitation-Augmented Language Models](https://arxiv.org/abs/2210.01296) (Oct 2022)
+  - [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629) (Oct 2022)
+  - [Prompting GPT-3 To Be Reliable](https://arxiv.org/abs/2210.09150) (Oct 2022)
+  - [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://arxiv.org/abs/2210.02406) (Oct 2022)
+  - [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://arxiv.org/abs/2210.01240v3) (Oct 2022)
+  - [Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples](https://arxiv.org/abs/2209.02128) (Sep 2022)
+  - [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://arxiv.org/abs/2209.14610) (Sep 2022)
+  - [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://arxiv.org/abs/2209.11755) (Sep 2022)
+  - [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://arxiv.org/abs/2208.03299) (Nov 2022)
+  - [DocPrompting: Generating Code by Retrieving the Docs](https://arxiv.org/abs/2207.05987) (July 2022)
+  - [On the Advance of Making Language Models Better Reasoners](https://arxiv.org/abs/2206.02336) (June 2022)
+  - [Large Language Models are Zero-Shot Reasoners](https://arxiv.org/abs/2205.11916) (May 2022)
+  - [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://arxiv.org/abs/2205.11822) (May 2022)
+  - [MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning](https://arxiv.org/abs/2205.00445) (May 2022)
+  - [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://aclanthology.org/2022.acl-long.576/) (Mqy 2022)
+  - [Toxicity Detection with Generative Prompt-based Inference](https://arxiv.org/abs/2205.12390) (May 2022)
+  - [Learning to Transfer Prompts for Text Generation](https://arxiv.org/abs/2205.01543) (May 2022)
+  - [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://arxiv.org/abs/2205.03401) (May 2022)
+  - [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://arxiv.org/abs/2204.13988) (Apr 2022)
+  - [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://arxiv.org/abs/2203.06566) (Mar 2022)
+  - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://arxiv.org/abs/2203.11171) (March 2022)
+  - [Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
+  - [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://arxiv.org/abs/2202.12837) (Feb 2022)
+  - [Chain of Thought Prompting Elicits Reasoning in Large Language Models](https://arxiv.org/abs/2201.11903) (Jan 2022)
+  - [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://arxiv.org/abs/2112.00114) (Nov 2021)
+  - [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://arxiv.org/abs/2110.01691) (Oct 2021)
+  - [Generated Knowledge Prompting for Commonsense Reasoning](https://arxiv.org/abs/2110.08387) (Oct 2021)
+  - [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://arxiv.org/abs/2110.08207) (Oct 2021)
+  - [Reframing Instructional Prompts to GPTk's Language](https://arxiv.org/abs/2109.07830) (Sep 2021)
+  - [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://arxiv.org/abs/2109.06977) (Sep 2021)
+  - [Making Pre-trained Language Models Better Few-shot Learners](https://aclanthology.org/2021.acl-long.295) (Aug 2021)
+  - [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://arxiv.org/abs/2104.08786) (April 2021)
+  - [BERTese: Learning to Speak to BERT](https://aclanthology.org/2021.eacl-main.316) (April 2021)
+  - [The Power of Scale for Parameter-Efficient Prompt Tuning](https://arxiv.org/abs/2104.08691) (April 2021)
+  - [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://arxiv.org/abs/2102.07350) (Feb 2021)
+  - [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://arxiv.org/abs/2102.09690) (Feb 2021)
+  - [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://arxiv.org/abs/2101.00190) (Jan 2021)
+  - [Learning to Generate Task-Specific Adapters from Task Description](https://arxiv.org/abs/2101.00420) (Jan 2021)
+  - [Making Pre-trained Language Models Better Few-shot Learners](https://arxiv.org/abs/2012.15723) (Dec 2020)
+  - [Learning from Task Descriptions](https://aclanthology.org/2020.emnlp-main.105/) (Nov 2020)
+  - [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://arxiv.org/abs/2010.15980) (Oct 2020)
+  - [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165) (May 2020)
+  - [How Can We Know What Language Models Know?](https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00324/96460/How-Can-We-Know-What-Language-Models-Know) (July 2020)
+  - [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361) (Jan 2020)
+
+## Uygulamalar
+  
+  - [BloombergGPT: A Large Language Model for Finance](https://arxiv.org/abs/2303.17564) (March 2023)
+  - [Medical Intervention Duration Estimation Using Language-enhanced Transformer Encoder with Medical Prompts](https://arxiv.org/abs/2303.17408) (March 2023)
+  - [Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes](https://arxiv.org/abs/2303.15846) (March 2023)
+  - [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://arxiv.org/abs/2303.16434) (March 2023)
+  - [Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning](https://arxiv.org/abs/2303.16445) (March 2023)
+  - [Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses](https://arxiv.org/abs/2303.15587) (March 2023)
+  - [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://arxiv.org/abs/2303.14375) (March 2023)
+  - [Debiasing Scores and Prompts of 2D Diffusion for Robust Text-to-3D Generation](https://arxiv.org/abs/2303.15413) (March 2023)
+  - [Zero-shot Model Diagnosis](https://arxiv.org/abs/2303.15441#) (March 2023)
+  - [Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages](https://arxiv.org/abs/2303.13592) (March 2023)
+  - [SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes Summarization](https://arxiv.org/abs/2303.13035) (March 2023)
+  - [Large Language Models and Simple, Stupid Bugs](https://arxiv.org/abs/2303.11455) (March 2023)
+  - [Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?](https://arxiv.org/abs/2303.09325) (Mar 2023)
+  - [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://arxiv.org/abs/2303.08896) (Mar 2023)
+  - [Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification](https://arxiv.org/abs/2303.07142) (March 2023)
+  - [ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction](https://arxiv.org/abs/2303.05063) (March 2023)
+  - [MathPrompter: Mathematical Reasoning using Large Language Models](https://arxiv.org/abs/2303.05398) (March 2023)
+  - [Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forums](https://arxiv.org/abs/2303.05400) (March 2023)
+  - [Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting](https://arxiv.org/abs/2303.03199) (March 2023)
+  - [Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering](https://arxiv.org/abs/2303.01903) (March 2023)
+  - [Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis](https://arxiv.org/abs/2303.00815) (March 2023)
+  - [SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks](https://arxiv.org/abs/2303.00733) (March 2023)
+  - [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://arxiv.org/abs/2302.14233) (Feb 2023)
+  - [Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models](https://arxiv.org/abs/2302.13439) (Feb 2023)
+  - [TabGenie: A Toolkit for Table-to-Text Generation](https://arxiv.org/abs/2302.14169) (Feb 2023)
+  - [SGL-PT: A Strong Graph Learner with Graph Prompt Tuning](https://arxiv.org/abs/2302.12449) (Feb 2023)
+  - [Few-Shot Table-to-Text Generation with Prompt-based Adapter](https://arxiv.org/abs/2302.12468) (Feb 2023)
+  - [Language Models Are Few-shot Learners for Prognostic Prediction](https://arxiv.org/abs/2302.12692) (Feb 2023)
+  - [STA: Self-controlled Text Augmentation for Improving Text Classifications](https://arxiv.org/abs/2302.12784) (Feb 2023)
+  - [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://arxiv.org/abs/2302.12813) (Feb 2023)
+  - [How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study](https://arxiv.org/abs/2302.10916) (Feb 2023) 
+  - [Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales](https://arxiv.org/abs/2302.08961) (Feb 2023)
+  - [LabelPrompt: Effective Prompt-based Learning for Relation Classification](https://arxiv.org/abs/2302.08068) (Feb 2023)
+  - [Language Model Crossover: Variation through Few-Shot Prompting](https://arxiv.org/abs/2302.09236) (Feb 2023)
+  - [Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition](https://arxiv.org/abs/2302.08102) (Feb 2023)
+  - [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
+  - [Prompting for Multimodal Hateful Meme Classification](https://arxiv.org/abs/2302.04156) (Feb 2023)
+  - [PLACES: Prompting Language Models for Social Conversation Synthesis](https://arxiv.org/abs/2302.03269) (Feb 2023)
+  - [Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation](https://arxiv.org/abs/2302.01441) (Feb 2023)
+  - [Crawling the Internal Knowledge-Base of Language Models](https://arxiv.org/abs/2301.12810) (Jan 2023)
+  - [Legal Prompt Engineering for Multilingual Legal Judgement Prediction](https://arxiv.org/abs/2212.02199) (Dec 2022)
+  - [Investigating Prompt Engineering in Diffusion Models](https://arxiv.org/abs/2211.15462) (Nov 2022)
+  - [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://arxiv.org/abs/2209.09513v2) (Sep 2022)
+  - [Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language](https://arxiv.org/abs/2210.15157) (Oct 2022)
+  - [Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?](https://arxiv.org/abs/2210.14699) (Oct 2022)
+  - [Plot Writing From Scratch Pre-Trained Language Models](https://aclanthology.org/2022.inlg-main.5) (July 2022)
+  - [Survey of Hallucination in Natural Language Generation](https://arxiv.org/abs/2202.03629) (Feb 2022)
+
+## Koleksiyonlar
+
+  - [Chain-of-Thought Papers](https://github.com/Timothyxxx/Chain-of-ThoughtsPapers)
+  - [Papers with Code](https://paperswithcode.com/task/prompt-engineering)
+  - [Prompt Papers](https://github.com/thunlp/PromptPapers#papers)
diff --git a/pages/readings.tr.mdx b/pages/readings.tr.mdx
new file mode 100644
index 0000000..379add3
--- /dev/null
+++ b/pages/readings.tr.mdx
@@ -0,0 +1,114 @@
+# Ek Okumalar
+#### (İsme göre sıralama yapıldı)
+
+- [2023 AI Index Report](https://aiindex.stanford.edu/report/)
+- [3 Principles for prompt engineering with GPT-3](https://www.linkedin.com/pulse/3-principles-prompt-engineering-gpt-3-ben-whately)
+- [A beginner-friendly guide to generative language models - LaMBDA guide](https://aitestkitchen.withgoogle.com/how-lamda-works)
+- [A Complete Introduction to Prompt Engineering for Large Language Models](https://www.mihaileric.com/posts/a-complete-introduction-to-prompt-engineering)
+- [A Generic Framework for ChatGPT Prompt Engineering](https://medium.com/@thorbjoern.heise/a-generic-framework-for-chatgpt-prompt-engineering-7097f6513a0b)
+- [An SEO’s guide to ChatGPT prompts](https://searchengineland.com/chatgpt-prompts-seo-393523)
+- [Anyone can Design! With a little help from Generative AI](https://github.com/YashSharma/PromptEngineering)
+- [AI Content Generation](https://www.jonstokes.com/p/ai-content-generation-part-1-machine)
+- [AI's rise generates new job title: Prompt engineer](https://www.axios.com/2023/02/22/chatgpt-prompt-engineers-ai-job)
+- [AI Safety, RLHF, and Self-Supervision - Jared Kaplan | Stanford MLSys #79](https://www.youtube.com/watch?v=fqC3D-zNJUM&ab_channel=StanfordMLSysSeminars)
+- [Awesome Textual Instruction Learning Papers](https://github.com/RenzeLou/awesome-instruction-learning)
+- [Awesome ChatGPT Prompts](https://github.com/f/awesome-chatgpt-prompts)
+- [Best 100+ Stable Diffusion Prompts](https://mpost.io/best-100-stable-diffusion-prompts-the-most-beautiful-ai-text-to-image-prompts)
+- [Best practices for prompt engineering with OpenAI API](https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api)
+- [Building GPT-3 applications — beyond the prompt](https://medium.com/data-science-at-microsoft/building-gpt-3-applications-beyond-the-prompt-504140835560)
+- [Can AI really be protected from text-based attacks?](https://techcrunch.com/2023/02/24/can-language-models-really-be-protected-from-text-based-attacks/)
+- [ChatGPT, AI and GPT-3 Apps and use cases](https://gpt3demo.com)
+- [ChatGPT Prompts](https://twitter.com/aaditsh/status/1636398208648658945?s=20)
+- [ChatGPT Plugins Collection ⭐️ (unofficial)](https://github.com/logankilpatrick/ChatGPT-Plugins-Collection)
+- [CMU Advanced NLP 2022: Prompting](https://youtube.com/watch?v=5ef83Wljm-M&feature=shares)
+- [Common Sense as Dark Matter - Yejin Choi | Stanford MLSys #78](https://youtube.com/live/n4HakBqoCVg?feature=shares)
+- [Create images with your words – Bing Image Creator comes to the new Bing](https://blogs.microsoft.com/blog/2023/03/21/create-images-with-your-words-bing-image-creator-comes-to-the-new-bing/)
+- [Curtis64's set of prompt gists](https://gist.github.com/Curtis-64)
+- [CS324 - Large Language Models](https://stanford-cs324.github.io/winter2022/)
+- [CS 324 - Advances in Foundation Models](https://stanford-cs324.github.io/winter2023/)
+- [CS224N: Natural Language Processing with Deep Learning](https://web.stanford.edu/class/cs224n/)
+- [DALL·E 2 Prompt Engineering Guide](https://docs.google.com/document/d/11WlzjBT0xRpQhP9tFMtxzd0q6ANIdHPUBkMV-YB043U/edit#)
+- [DALL·E 2 Preview - Risks and Limitations](https://github.com/openai/dalle-2-preview/blob/main/system-card.md)
+- [DALLE Prompt Book](https://dallery.gallery/the-dalle-2-prompt-book)
+- [DALL-E, Make Me Another Picasso, Please](https://www.newyorker.com/magazine/2022/07/11/dall-e-make-me-another-picasso-please?)
+- [Diffusion Models: A Practical Guide](https://scale.com/guides/diffusion-models-guide)
+- [Exploiting GPT-3 Prompts](https://twitter.com/goodside/status/1569128808308957185)
+- [Exploring Prompt Injection Attacks](https://research.nccgroup.com/2022/12/05/exploring-prompt-injection-attacks)
+- [Extrapolating to Unnatural Language Processing with GPT-3's In-context Learning: The Good, the Bad, and the Mysterious](http://ai.stanford.edu/blog/in-context-learning)
+- [FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering](https://arxiv.org/pdf/2303.10699.pdf)
+- [Generative AI with Cohere: Part 1 - Model Prompting](https://txt.cohere.ai/generative-ai-part-1)
+- [Generative AI: Perspectives from Stanford HAI](https://hai.stanford.edu/sites/default/files/2023-03/Generative_AI_HAI_Perspectives.pdf)
+- [Get a Load of This New Job: "Prompt Engineers" Who Act as Psychologists to AI Chatbots](https://futurism.com/prompt-engineers-ai)
+- [Giving GPT-3 a Turing Test](https://lacker.io/ai/2020/07/06/giving-gpt-3-a-turing-test.html)
+- [GPT-3 & Beyond](https://youtube.com/watch?v=-lnHHWRCDGk)
+- [GPT3 and Prompts: A quick primer](https://buildspace.so/notes/intro-to-gpt3-prompts)
+- [Hands-on with Bing’s new ChatGPT-like features](https://techcrunch.com/2023/02/08/hands-on-with-the-new-bing/)
+- [How to Draw Anything](https://andys.page/posts/how-to-draw)
+- [How to get images that don't suck](https://www.reddit.com/r/StableDiffusion/comments/x41n87/how_to_get_images_that_dont_suck_a)
+- [How to make LLMs say true things](https://evanjconrad.com/posts/world-models)
+- [How to perfect your prompt writing for AI generators](https://www.sydney.edu.au/news-opinion/news/2023/02/28/how-to-perfect-your-prompt-writing-for-ai-generators.html)
+- [How to write good prompts](https://andymatuschak.org/prompts)
+- [If I Was Starting Prompt Engineering in 2023: My 8 Insider Tips](https://youtube.com/watch?v=SirW7feTjh0&feature=shares)
+- [Indirect Prompt Injection on Bing Chat](https://greshake.github.io/)
+- [Interactive guide to GPT-3 prompt parameters](https://sevazhidkov.com/interactive-guide-to-gpt-3-prompt-parameters)
+- [Introduction to Reinforcement Learning with Human Feedback](https://www.surgehq.ai/blog/introduction-to-reinforcement-learning-with-human-feedback-rlhf-series-part-1)
+- [In defense of prompt engineering](https://simonwillison.net/2023/Feb/21/in-defense-of-prompt-engineering/)
+- [JailBreaking ChatGPT: Everything You Need to Know](https://metaroids.com/learn/jailbreaking-chatgpt-everything-you-need-to-know/)
+- [Language Models and Prompt Engineering: Systematic Survey of Prompting Methods in NLP](https://youtube.com/watch?v=OsbUfL8w-mo&feature=shares)
+- [Language Model Behavior: A Comprehensive Survey](https://arxiv.org/abs/2303.11504)
+- [Learn Prompting](https://learnprompting.org)
+- [Meet Claude: Anthropic’s Rival to ChatGPT](https://scale.com/blog/chatgpt-vs-claude)
+- [Methods of prompt programming](https://generative.ink/posts/methods-of-prompt-programming)
+- [Mysteries of mode collapse](https://www.lesswrong.com/posts/t9svvNPNmFf5Qa3TA/mysteries-of-mode-collapse)
+- [NLP for Text-to-Image Generators: Prompt Analysis](https://heartbeat.comet.ml/nlp-for-text-to-image-generators-prompt-analysis-part-1-5076a44d8365)
+- [NLP with Deep Learning CS224N/Ling284 - Lecture 11: Promting, Instruction Tuning, and RLHF](http://web.stanford.edu/class/cs224n/slides/cs224n-2023-lecture11-prompting-rlhf.pdf)
+- [Notes for Prompt Engineering by sw-yx](https://github.com/sw-yx/ai-notes)
+- [On pitfalls (and advantages) of sophisticated large language models](https://arxiv.org/abs/2303.17511)
+- [OpenAI Cookbook](https://github.com/openai/openai-cookbook)
+- [OpenAI Prompt Examples for several applications](https://platform.openai.com/examples)
+- [Pretrain, Prompt, Predict -  A New Paradigm for NLP](http://pretrain.nlpedia.ai)
+- [Prompt Engineer: Tech's hottest job title?](https://www.peoplematters.in/article/talent-management/is-prompt-engineering-the-hottest-job-in-ai-today-37036)
+- [Prompt Engineering by Lilian Weng](https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/)
+- [Prompt Engineering 101 - Introduction and resources](https://www.linkedin.com/pulse/prompt-engineering-101-introduction-resources-amatriain)
+- [Prompt Engineering 101: Autocomplete, Zero-shot, One-shot, and Few-shot prompting](https://youtube.com/watch?v=v2gD8BHOaX4&feature=shares)
+- [Prompt Engineering 101](https://humanloop.com/blog/prompt-engineering-101)
+- [Prompt Engineering - A new profession ?](https://www.youtube.com/watch?v=w102J3_9Bcs&ab_channel=PatrickDebois)
+- [Prompt Engineering by co:here](https://docs.cohere.ai/docs/prompt-engineering)
+- [Prompt Engineering by Microsoft](https://microsoft.github.io/prompt-engineering)
+- [Prompt Engineering: The Career of Future](https://shubhamsaboo111.medium.com/prompt-engineering-the-career-of-future-2fb93f90f117)
+- [Prompt engineering davinci-003 on our own docs for automated support (Part I)](https://www.patterns.app/blog/2022/12/21/finetune-llm-tech-support)
+- [Prompt Engineering Guide: How to Engineer the Perfect Prompts](https://richardbatt.co.uk/prompt-engineering-guide-how-to-engineer-the-perfect-prompts)
+- [Prompt Engineering in GPT-3](https://www.analyticsvidhya.com/blog/2022/05/prompt-engineering-in-gpt-3)
+- [Prompt Engineering Template](https://docs.google.com/spreadsheets/d/1-snKDn38-KypoYCk9XLPg799bHcNFSBAVu2HVvFEAkA/edit#gid=0)
+- [Prompt Engineering Topic by GitHub](https://github.com/topics/prompt-engineering)
+- [Prompt Engineering: The Ultimate Guide 2023 [GPT-3 & ChatGPT]](https://businessolution.org/prompt-engineering/)
+- [Prompt Engineering: From Words to Art](https://www.saxifrage.xyz/post/prompt-engineering)
+- [Prompt Engineering with OpenAI's GPT-3 and other LLMs](https://youtube.com/watch?v=BP9fi_0XTlw&feature=shares)
+- [Prompt injection attacks against GPT-3](https://simonwillison.net/2022/Sep/12/prompt-injection)
+- [Prompt injection to read out the secret OpenAI API key](https://twitter.com/ludwig_stumpp/status/1619701277419794435?s=20&t=GtoMlmYCSt-UmvjqJVbBSA)
+- [Prompting: Better Ways of Using Language Models for NLP Tasks](https://thegradient.pub/prompting/)
+- [Prompting for Few-shot Learning](https://www.cs.princeton.edu/courses/archive/fall22/cos597G/lectures/lec05.pdf)
+- [Prompting in NLP: Prompt-based zero-shot learning](https://savasy-22028.medium.com/prompting-in-nlp-prompt-based-zero-shot-learning-3f34bfdb2b72)
+- [Prompting Methods with Language Models and Their Applications to Weak Supervision](https://snorkel.ai/prompting-methods-with-language-models-nlp)
+- [Prompts as Programming by Gwern](https://www.gwern.net/GPT-3#prompts-as-programming)
+- [Prompts for communicators using the new AI-powered Bing](https://blogs.microsoft.com/blog/2023/03/16/prompts-for-communicators-using-the-new-ai-powered-bing/)
+- [Reverse Prompt Engineering for Fun and (no) Profit](https://lspace.swyx.io/p/reverse-prompt-eng)
+- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://arxiv.org/pdf/2303.10868.pdf)
+- [So you want to be a prompt engineer: Critical careers of the future](https://venturebeat.com/ai/so-you-want-to-be-a-prompt-engineer-critical-careers-of-the-future/)
+- [Simulators](https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators)
+- [Start with an Instruction](https://beta.openai.com/docs/quickstart/start-with-an-instruction)
+- [Talking to machines: prompt engineering & injection](https://artifact-research.com/artificial-intelligence/talking-to-machines-prompt-engineering-injection)
+- [Tech’s hottest new job: AI whisperer. No coding required](https://www.washingtonpost.com/technology/2023/02/25/prompt-engineers-techs-next-big-job/)
+- [The Book - Fed Honeypot](https://fedhoneypot.notion.site/25fdbdb69e9e44c6877d79e18336fe05?v=1d2bf4143680451986fd2836a04afbf4)
+- [The ChatGPT Prompt Book](https://docs.google.com/presentation/d/17b_ocq-GL5lhV_bYSShzUgxL02mtWDoiw9xEroJ5m3Q/edit#slide=id.gc6f83aa91_0_79)
+- [The ChatGPT list of lists: A collection of 3000+ prompts, examples, use-cases, tools, APIs, extensions, fails and other resources](https://medium.com/mlearning-ai/the-chatgpt-list-of-lists-a-collection-of-1500-useful-mind-blowing-and-strange-use-cases-8b14c35eb)
+- [The Most Important Job Skill of This Century](https://www.theatlantic.com/technology/archive/2023/02/openai-text-models-google-search-engine-bard-chatbot-chatgpt-prompt-writing/672991/)
+- [The Mirror of Language](https://deepfates.com/the-mirror-of-language)
+- [The Waluigi Effect (mega-post)](https://www.lesswrong.com/posts/D7PumeYTDPfBTp3i7/the-waluigi-effect-mega-post)
+- [Thoughts and impressions of AI-assisted search from Bing](https://simonwillison.net/2023/Feb/24/impressions-of-bing/)
+- [Unleash Your Creativity with Generative AI: Learn How to Build Innovative Products!](https://youtube.com/watch?v=jqTkMpziGBU&feature=shares)
+- [Unlocking Creativity with Prompt Engineering](https://youtube.com/watch?v=PFsbWAC4_rk&feature=shares)
+- [Using GPT-Eliezer against ChatGPT Jailbreaking](https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking)
+- [What Is ChatGPT Doing … and Why Does It Work?](https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/)
+- [Why is ChatGPT so good?](https://scale.com/blog/chatgpt-reinforcement-learning)
+- [【徹底解説】これからのエンジニアの必携スキル、プロンプトエンジニアリングの手引「Prompt Engineering Guide」を読んでまとめてみた](https://dev.classmethod.jp/articles/how-to-design-prompt-engineering/)
diff --git a/pages/risks.tr.mdx b/pages/risks.tr.mdx
new file mode 100644
index 0000000..168f3ad
--- /dev/null
+++ b/pages/risks.tr.mdx
@@ -0,0 +1,12 @@
+# Riskler ve Yanlış Kullanımlar
+
+import { Callout } from 'nextra-theme-docs'
+
+Birkaç adımda öğrenme ve düşünce zinciri yoluyla yönlendirme gibi teknikler kullanılarak çeşitli görevler için iyi hazırlanmış bilgi istemlerinin ne kadar etkili olabileceğini zaten gördük. LLM'lerin üzerine gerçek dünya uygulamaları inşa etmeyi düşündüğümüzde, dil modelleriyle ilgili yanlış kullanımlar, riskler ve güvenlik uygulamaları hakkında düşünmek çok önemli hale geliyor.
+
+
+Bu bölüm, hızlı enjeksiyonlar gibi teknikler yoluyla LLM'lerin bazı risklerini ve yanlış kullanımlarını vurgulamaya odaklanmaktadır. Ayrıca, zararlı davranışları ve bunların etkili yönlendirme teknikleriyle potansiyel olarak nasıl hafifletilebileceğini vurgular. İlgilenilen diğer konular arasında genellenebilirlik, kalibrasyon, önyargılar, sosyal önyargılar ve gerçeklik sayılabilir.
+
+<Callout emoji="⚠️">
+  Bu bölüm yoğun geliştirme aşamasındadır.
+</Callout>
diff --git a/pages/risks/_meta.tr.json b/pages/risks/_meta.tr.json
new file mode 100644
index 0000000..29a5ff4
--- /dev/null
+++ b/pages/risks/_meta.tr.json
@@ -0,0 +1,6 @@
+{
+    "adversarial": "Adversarial Prompting",
+    "factuality": "Factuality",
+    "biases": "Biases"
+}
+  
\ No newline at end of file
diff --git a/pages/risks/adversarial.tr.mdx b/pages/risks/adversarial.tr.mdx
new file mode 100644
index 0000000..6cf330d
--- /dev/null
+++ b/pages/risks/adversarial.tr.mdx
@@ -0,0 +1,3 @@
+# Adversarial Prompting
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/risks/biases.tr.mdx b/pages/risks/biases.tr.mdx
new file mode 100644
index 0000000..7f05631
--- /dev/null
+++ b/pages/risks/biases.tr.mdx
@@ -0,0 +1,98 @@
+# Yanlılıklar
+
+LLM'ler, potansiyel olarak zararlı olabilecek sorunlu nesiller üretebilir ve aşağı akış görevlerinde modelin performansını bozabilecek önyargılar gösterebilir. Bunlardan bazıları, etkili yönlendirme stratejileriyle hafifletilebilir, ancak denetleme ve filtreleme gibi daha gelişmiş çözümler gerektirebilir. 
+
+### Örneklerin Dağılımı
+Birkaç aşamalı öğrenme gerçekleştirirken, örneklerin dağılımı modelin performansını etkiler mi veya modeli bir şekilde saptırır mı? Burada basit bir test yapabiliriz.
+
+*Bilgi İstemcisi:*
+```
+S: Şimdiye kadarki en iyi haberi aldım!
+C: Olumlu
+
+S: İş yerinde zam aldık!
+C: Olumlu
+
+S: Bugün başardıklarımla gurur duyuyorum.
+C: Olumlu
+
+S: Şimdiye kadarki en iyi günü yaşıyorum!
+C: Olumlu
+
+S: Gerçekten hafta sonunu dört gözle bekliyorum.
+C: Olumlu
+
+S: Şimdiye kadarki en iyi hediyeyi aldım!
+C: Olumlu
+
+S: Şu an çok mutluyum.
+C: Olumlu
+
+S: Böyle harika bir aileye sahip olduğum için çok şanslıyım.
+C: Olumlu
+
+S: Dışarda hava çok kasvetli.
+C: Olumsuz
+
+S: Az önce korkunç bir haber aldım.
+C: Olumsuz
+
+S: Ekşi bir tat bıraktı.
+C: 
+```
+
+*Çıktı:*
+```
+Olumsuz
+```
+
+Yukarıdaki örnekte, örneklerin dağılımı modeli saptırmıyor gibi görünüyor. Bu güzel. Sınıflandırması daha zor bir metinle başka bir örnek deneyelim ve modelin nasıl yaptığına bakalım:
+
+*Bilgi İstemi:*
+```
+S: Buradaki yemek lezzetli!
+C: Olumlu 
+
+S: Bu ders çalışmasından çok sıkıldım.
+C: Olumsuz
+
+S: Sınavda başarısız olduğuma inanamıyorum.
+C: Olumsuz
+
+S: Bugün harika bir gün geçirdim!
+C: Olumlu 
+
+S: Bu işten nefret ediyorum.
+C: Olumsuz
+
+S: Buradaki servis iğrenç.
+C: Olumsuz
+
+S: Hayatımdan çok hayal kırıklığına uğradım.
+C: Olumsuz
+
+S: Hiç ara vermiyorum.
+C: Olumsuz
+
+S: Bu yemeğin tadı berbat.
+C: Olumsuz
+
+S: Patronuma dayanamıyorum.
+C: Olumsuz
+
+S: Bir şey hissediyorum.
+Ç:
+```
+
+*Çıktı:*
+```
+Olumsuz
+```
+
+Bu son cümle biraz öznel olsa da, dağılımı ters çevirdim ve bunun yerine 8 olumlu örnek ve 2 olumsuz örnek kullandım ve ardından aynı cümleyi tekrar denedim. Bilin bakalım model ne cevap verdi? "Olumlu" yanıtını verdi. Model, duygu sınıflandırması hakkında çok fazla bilgiye sahip olabilir, bu nedenle bu problem için önyargı göstermesini sağlamak zor olacaktır. Buradaki tavsiye, dağılımı çarpıtmaktan kaçınmak ve bunun yerine her etiket için daha dengeli sayıda örnek sağlamaktır. Modelin çok fazla bilgi sahibi olmadığı daha zor görevler için muhtemelen daha fazla mücadele edecektir.
+
+
+### Örnekler Sırası
+Few-shot learning gerçekleştirirken, sıra modelin performansını etkiler mi veya modeli bir şekilde saptırır mı?
+
+Yukarıdaki örnekleri deneyebilir ve sırayı değiştirerek modelin bir etikete eğilimli olmasını sağlayıp sağlayamayacağınızı görebilirsiniz. Tavsiye, örnekleri rastgele sıralamaktır. Örneğin, önce tüm olumlu örneklere, sonra olumsuz örneklere sahip olmaktan kaçının. Etiketlerin dağılımı çarpıksa bu sorun daha da büyür. Bu tür önyargıları azaltmak için her zaman çok şey denediğinizden emin olun.
diff --git a/pages/risks/factuality.en.mdx b/pages/risks/factuality.en.mdx
index fd20a61..fdaa34f 100644
--- a/pages/risks/factuality.en.mdx
+++ b/pages/risks/factuality.en.mdx
@@ -18,9 +18,9 @@ Q: Who is Alvan Muntz?
 A: ? 
 
 Q: What is Kozar-09? 
-A: ? Q: 
+A: ? 
 
-How many moons does Mars have? 
+Q: How many moons does Mars have? 
 A: Two, Phobos and Deimos. 
 
 Q: Who is Neto Beto Roberto? 
diff --git a/pages/risks/factuality.tr.mdx b/pages/risks/factuality.tr.mdx
new file mode 100644
index 0000000..842e00e
--- /dev/null
+++ b/pages/risks/factuality.tr.mdx
@@ -0,0 +1,34 @@
+# Gerçeklik
+
+LLM'ler kulağa tutarlı ve inandırıcı gelen ancak bazen uydurulabilen yanıtlar üretme eğilimindedir. Yönlendirmelerin iyileştirilmesi, modelin daha doğru/gerçeğe dayalı yanıtlar üretecek şekilde geliştirilmesine yardımcı olabilir ve tutarsız ve uydurulmuş yanıtlar üretme olasılığını azaltabilir.
+
+Bazı çözümler şunları içerebilir:
+- modelin uydurma metin üretme olasılığını azaltmak için bağlamın bir parçası olarak temel gerçeği (ör. ilgili makale paragrafı veya Wikipedia girişi) sağlayın.
+- modeli, olasılık parametrelerini azaltarak ve cevabı bilmediğini kabul etmesini söyleyerek (örneğin, "Bilmiyorum") daha az çeşitli yanıtlar üretecek şekilde yapılandırın.
+- bilgi isteminde, bilebileceği ve bilmediği soru ve yanıt örneklerinin bir kombinasyonunu sağlayın
+
+Basit bir örneğe bakalım:
+
+*Bilgi istemi:*
+```
+S: Atom nedir?
+C: Atom, her şeyi oluşturan küçük bir parçacıktır. 
+
+S: Alvan Muntz kimdir?
+C: ? 
+
+S: Kozar-09 nedir?
+C: ?
+
+Q: Mars'ın kaç uydusu var?
+C: İki, Phobos ve Deimos. 
+
+S: Neto Beto Roberto kimdir? 
+```
+
+*Çıktı:*
+```
+C: ?
+```
+
+Bu örnekte modelin doğru olması için "Neto Beto Roberto" adını ben uydurdum. Soruyu biraz değiştirmeye çalışın ve çalışıp çalışamayacağınıza bakın. Şimdiye kadar öğrendiklerinize dayanarak bunu daha da geliştirmenin farklı yolları vardır.
\ No newline at end of file
diff --git a/pages/techniques.tr.mdx b/pages/techniques.tr.mdx
new file mode 100644
index 0000000..138bab0
--- /dev/null
+++ b/pages/techniques.tr.mdx
@@ -0,0 +1,5 @@
+# Bilgi İstemcisi Teknikleri
+
+Bu noktada, farklı görevlerde daha iyi sonuçlar almak için istemleri iyileştirmeye yardımcı olduğu açık olmalıdır. Hızlı mühendisliğin arkasındaki tüm fikir budur.
+
+Temel örnekler eğlenceli olsa da, bu bölümde daha karmaşık ve ilginç görevleri başarmamızı sağlayan daha gelişmiş yönlendirme mühendisliği tekniklerini ele alıyoruz.
\ No newline at end of file
diff --git a/pages/techniques/_meta.tr.json b/pages/techniques/_meta.tr.json
new file mode 100644
index 0000000..3a672e7
--- /dev/null
+++ b/pages/techniques/_meta.tr.json
@@ -0,0 +1,14 @@
+{
+    "zeroshot": "Zero-shot Prompting",
+    "fewshot": "Few-shot Prompting",
+    "cot": "Chain-of-Thought Prompting",
+    "consistency": "Self-Consistency",
+    "knowledge": "Generate Knowledge Prompting",
+    "ape": "Automatic Prompt Engineer",
+    "activeprompt": "Active-Prompt",
+    "dsp": "Directional Stimulus Prompting",
+    "react": "ReAct",
+    "multimodalcot": "Multimodal CoT",
+    "graph": "Graph Prompting"
+}
+  
\ No newline at end of file
diff --git a/pages/techniques/activeprompt.tr.mdx b/pages/techniques/activeprompt.tr.mdx
new file mode 100644
index 0000000..841c5db
--- /dev/null
+++ b/pages/techniques/activeprompt.tr.mdx
@@ -0,0 +1,12 @@
+# Aktif-Bilgi İstemi
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import ACTIVE from '../../img/active-prompt.png'
+
+Düşünce zinciri (CoT) yöntemleri, sabit bir insan açıklamalı örnekler kümesine dayanır. Bununla ilgili sorun, örneklerin farklı görevler için en etkili örnekler olmayabilmesidir. Bunu ele almak için [Diao ve diğerleri, (2023)](https://arxiv.org/pdf/2302.12246.pdf) kısa süre önce, LLM'leri göreve özgü farklı örnek istemlere uyarlamak için Active-Prompt adlı yeni bir yönlendirme yaklaşımı önerdi ( insan tarafından tasarlanmış CoT muhakemesi ile açıklamalı).
+
+Aşağıda yaklaşımın bir örneği verilmiştir. İlk adım, LLM'yi birkaç CoT örneği olsun ya da olmasın sorgulamaktır. Bir dizi eğitim sorusu için *k* olası cevaplar üretilir. *k* yanıtlarına (kullanılan uyuşmazlık) dayalı olarak bir belirsizlik ölçüsü hesaplanır. En belirsiz sorular, insanlar tarafından ek açıklama için seçilir. Yeni açıklamalı örnekler daha sonra her soruyu anlamak için kullanılır.
+
+<Screenshot src={ACTIVE} alt="ACTIVE" />
+Resim Kaynağı: [Diao et al., (2023)](https://arxiv.org/pdf/2302.12246.pdf)
\ No newline at end of file
diff --git a/pages/techniques/ape.tr.mdx b/pages/techniques/ape.tr.mdx
new file mode 100644
index 0000000..0286fa6
--- /dev/null
+++ b/pages/techniques/ape.tr.mdx
@@ -0,0 +1,26 @@
+# Otomatik Bilgi İstemi Mühendisi (APE)
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import APE from '../../img/APE.png'
+import APECOT from '../../img/ape-zero-shot-cot.png'
+
+<Screenshot src={APE} alt="APE" />
+Resim Kaynağı: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
+
+[Zhou et al., (2022)](https://arxiv.org/abs/2211.01910) otomatik yönerge oluşturma ve seçme için otomatik bilgi istemi mühendisliği (APE) çerçevesi önermek. Yönerge üretme problemi, aday çözümler üretmek ve üzerinde araştırma yapmak için LLM'leri kullanan bir kara kutu optimizasyon problemi olarak ele alınan doğal dil sentezi olarak çerçevelenir.
+
+İlk adım, bir görev için talimat adayları oluşturmak üzere çıktı gösterileri verilen büyük bir dil modelini (bir çıkarım modeli olarak) içerir. Bu aday çözümler, arama prosedürünü yönlendirecektir. Talimatlar bir hedef model kullanılarak yürütülür ve ardından hesaplanan değerlendirme puanlarına göre en uygun talimat seçilir.
+
+APE, insan tarafından tasarlanmış "Adım adım düşünelim" isteminden daha iyi bir sıfır vuruşlu CoT istemi keşfeder ([Kojima ve diğerleri, 2022](https://arxiv.org/abs/2205.11916)).
+
+"Doğru cevaba sahip olduğumuzdan emin olmak için bunu adım adım çözelim." zincirleme akıl yürütmeyi ortaya çıkarır ve MultiArith ve GSM8K kıyaslamalarında performansı artırır:
+
+<Screenshot src={APECOT} alt="APECOT" />
+Resim Kaynağı: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
+
+Bu makale, bilgi istemlerini otomatik olarak optimize etme fikri olan bilgi istemi mühendisliği ile ilgili önemli bir konuya değinmektedir. Bu kılavuzda bu konuya derinlemesine girmesek de, konuyla ilgileniyorsanız işte birkaç önemli makale:
+
+- [AutoPrompt](https://arxiv.org/abs/2010.15980) - gradyan kılavuzlu aramaya dayalı olarak çeşitli görevler için istemleri otomatik olarak oluşturmaya yönelik bir yaklaşım önerir.
+- [Prefix Tuning](https://arxiv.org/abs/2101.00190) - NLG görevleri için eğitilebilir bir sürekli ön ekin başına eklenen ince ayara hafif bir alternatif. 
+- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - geri yayılım yoluyla yumuşak bilgi istemlerini öğrenmek için bir mekanizma önerir.
\ No newline at end of file
diff --git a/pages/techniques/consistency.tr.mdx b/pages/techniques/consistency.tr.mdx
new file mode 100644
index 0000000..c3c889f
--- /dev/null
+++ b/pages/techniques/consistency.tr.mdx
@@ -0,0 +1,3 @@
+# Self-Consistency
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/techniques/cot.tr.mdx b/pages/techniques/cot.tr.mdx
new file mode 100644
index 0000000..7f8044a
--- /dev/null
+++ b/pages/techniques/cot.tr.mdx
@@ -0,0 +1,3 @@
+# Chain-of-Thought Prompting
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/techniques/dsp.tr.mdx b/pages/techniques/dsp.tr.mdx
new file mode 100644
index 0000000..2c1b15b
--- /dev/null
+++ b/pages/techniques/dsp.tr.mdx
@@ -0,0 +1,16 @@
+# Directional Stimulus Prompting
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import DSP from '../../img/dsp.jpeg'
+
+[Li et al., (2023)](https://arxiv.org/abs/2302.11520) istenen özeti oluşturmada LLM'ye daha iyi rehberlik etmek için yeni bir yönlendirme tekniği önermektedir.
+
+Ayarlanabilir bir politika LM, uyaran/ipucu oluşturmak için eğitilir. LLM'leri optimize etmek için RL'nin daha fazla kullanıldığını görmek.
+
+Aşağıdaki şekil, Yönlü Uyaran İsteminin standart yönlendirmeyle karşılaştırmasını göstermektedir. Politika LM'si küçük olabilir ve bir kara kutu dondurulmuş LLM'ye rehberlik eden ipuçlarını oluşturmak için optimize edilebilir.
+
+<Screenshot src={DSP} alt="DSP" />
+Resim Kaynağı: [Li et al., (2023)](https://arxiv.org/abs/2302.11520)
+
+Tam örnek çok yakında!
\ No newline at end of file
diff --git a/pages/techniques/fewshot.tr.mdx b/pages/techniques/fewshot.tr.mdx
new file mode 100644
index 0000000..15a092d
--- /dev/null
+++ b/pages/techniques/fewshot.tr.mdx
@@ -0,0 +1,3 @@
+# Few-Shot Prompting
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/techniques/graph.tr.mdx b/pages/techniques/graph.tr.mdx
new file mode 100644
index 0000000..c88b7ba
--- /dev/null
+++ b/pages/techniques/graph.tr.mdx
@@ -0,0 +1,5 @@
+# GraphPrompts
+
+[Liu et al., 2023](https://arxiv.org/abs/2302.08043) aşağı akış görevlerinde performansı artırmak için grafikler için yeni bir yönlendirme çerçevesi olan GraphPrompt'ı sunar.
+
+Daha fazlası yakında!
\ No newline at end of file
diff --git a/pages/techniques/knowledge.tr.mdx b/pages/techniques/knowledge.tr.mdx
new file mode 100644
index 0000000..d11f7b7
--- /dev/null
+++ b/pages/techniques/knowledge.tr.mdx
@@ -0,0 +1,3 @@
+# Generated Knowledge Prompting
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/pages/techniques/multimodalcot.tr.mdx b/pages/techniques/multimodalcot.tr.mdx
new file mode 100644
index 0000000..df3f00e
--- /dev/null
+++ b/pages/techniques/multimodalcot.tr.mdx
@@ -0,0 +1,15 @@
+# Çok Modlu CoT Bilgi İstemi
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import MCOT from '../../img/multimodal-cot.png'
+
+[Zhang et al. (2023)](https://arxiv.org/abs/2302.00923) yakın zamanda çok modlu bir düşünce zinciri yönlendirme yaklaşımı önerdi. Geleneksel CoT, dil yöntemine odaklanır. Buna karşılık, Multimodal CoT, metin ve vizyonu iki aşamalı bir çerçevede birleştirir. İlk adım, çok modlu bilgilere dayalı gerekçe oluşturmayı içerir. Bunu, bilgilendirici olarak oluşturulmuş gerekçelerden yararlanan ikinci aşama olan cevap çıkarımı izler.
+
+Multimodal CoT modeli (1B), ScienceQA kıyaslamasında GPT-3.5'ten daha iyi performans gösterir.
+
+<Screenshot src={MCOT} alt="MCOT" />
+Resim Kaynağı: [Zhang et al. (2023)](https://arxiv.org/abs/2302.00923)
+
+Daha Fazla Bilgi:
+- [Language Is Not All You Need: Aligning Perception with Language Models](https://arxiv.org/abs/2302.14045) (Feb 2023)
\ No newline at end of file
diff --git a/pages/techniques/react.tr.mdx b/pages/techniques/react.tr.mdx
new file mode 100644
index 0000000..17cbd74
--- /dev/null
+++ b/pages/techniques/react.tr.mdx
@@ -0,0 +1,15 @@
+# ReAct
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+import {Screenshot} from 'components/screenshot'
+import REACT from '../../img/react.png'
+
+[Yao et al., 2022](https://arxiv.org/abs/2210.03629) LLM'lerin hem muhakeme izlerini hem de göreve özgü eylemleri serpiştirilmiş bir şekilde oluşturmak için kullanıldığı bir çerçeve tanıttı. Akıl yürütme izlerinin oluşturulması, modelin eylem planlarını başlatmasına, izlemesine ve güncellemesine ve hatta istisnaları ele almasına olanak tanır. Eylem adımı, bilgi tabanları veya ortamlar gibi dış kaynaklarla arayüz oluşturmaya ve bunlardan bilgi toplamaya izin verir.
+
+
+ReAct kütüphanesi, LLM'lerin daha güvenilir ve olgusal yanıtlara yol açan ek bilgileri almak için harici araçlarla etkileşime girmesine izin verebilir.
+
+<Screenshot src={REACT} alt="REACT" />
+Resim Kaynağı: [Yao et al., 2022](https://arxiv.org/abs/2210.03629)
+
+Tam örnek çok yakında!
\ No newline at end of file
diff --git a/pages/techniques/zeroshot.tr.mdx b/pages/techniques/zeroshot.tr.mdx
new file mode 100644
index 0000000..abee3cb
--- /dev/null
+++ b/pages/techniques/zeroshot.tr.mdx
@@ -0,0 +1,21 @@
+# Zero-Shot Bilgi İstemi
+Günümüzde büyük miktarda veri üzerinde eğitilen ve talimatları takip edecek şekilde ayarlanan LLM'ler, görevleri sıfır atışla gerçekleştirme yeteneğine sahiptir. Önceki bölümde birkaç sıfır atış örneği denedik. İşte kullandığımız örneklerden biri:
+
+*Bilgi İstemi:*
+```
+Metni nötr, negatif veya pozitif olarak sınıflandırın.
+
+Metin: Bence tatil tamam.
+Duygusallık:
+```
+
+*Çıktı:*
+```
+Nötr
+```
+
+Yukarıdaki istemde, modele herhangi bir örnek vermediğimize dikkat edin -- bu, iş başındaki sıfır atış yetenekleridir.
+
+Talimat ayarlamanın sıfır vuruşlu öğrenmeyi iyileştirdiği gösterilmiştir [Wei et al. (2022)](https://arxiv.org/pdf/2109.01652.pdf). Talimat ayarlama, esas olarak, talimatlar aracılığıyla açıklanan veri kümeleri üzerindeki ince ayar modellerinin konseptidir. Ayrıca, [RLHF](https://arxiv.org/abs/1706.03741) (insan geri bildiriminden pekiştirmeli öğrenme), modelin insan tercihlerine daha iyi uyacak şekilde hizalandığı talimat ayarını ölçeklendirmek için benimsenmiştir. Bu son gelişme, ChatGPT gibi modellere güç vermektedir. Tüm bu yaklaşımları ve yöntemleri önümüzdeki bölümlerde tartışacağız.
+
+Zero-shot çalışmadığında, bilgi isteminde few-shot istemine yol açan gösteriler veya örnekler sağlamanız önerilir. Bir sonraki bölümde, few-shot yönlendirmeyi gösteriyoruz.
\ No newline at end of file
diff --git a/pages/tools.tr.mdx b/pages/tools.tr.mdx
new file mode 100644
index 0000000..97d9acc
--- /dev/null
+++ b/pages/tools.tr.mdx
@@ -0,0 +1,41 @@
+# Araçlar & Kütüphaneler
+#### (İsme göre sıralandı)
+
+- [AI Test Kitchen](https://aitestkitchen.withgoogle.com)
+- [betterprompt](https://github.com/krrishdholakia/betterprompt)
+- [ChatGPT Prompt Generator](https://huggingface.co/spaces/merve/ChatGPT-prompt-generator)
+- [ClickPrompt](https://github.com/prompt-engineering/click-prompt)
+- [DreamStudio](https://beta.dreamstudio.ai)
+- [DUST](https://dust.tt)
+- [Dyno](https://trydyno.com)
+- [EmergentMind](https://www.emergentmind.com)
+- [EveryPrompt](https://www.everyprompt.com)
+- [GPT Index](https://github.com/jerryjliu/gpt_index)
+- [GPTTools](https://gpttools.com/comparisontool)
+- [hwchase17/adversarial-prompts](https://github.com/hwchase17/adversarial-prompts)
+- [Interactive Composition Explorer](https://github.com/oughtinc/ice)
+- [LangChain](https://github.com/hwchase17/langchain)
+- [Lexica](https://lexica.art)
+- [loom](https://github.com/socketteer/loom)
+- [Metaprompt](https://metaprompt.vercel.app/?task=gpt)
+- [OpenAI Playground](https://beta.openai.com/playground)
+- [OpenICL](https://github.com/Shark-NLP/OpenICL)
+- [OpenPrompt](https://github.com/thunlp/OpenPrompt)
+- [OpenPlayground](https://nat.dev/)
+- [Playground](https://playgroundai.com)
+- [Prodia](https://app.prodia.com/#/)
+- [Prompt Base](https://promptbase.com)
+- [Prompt Engine](https://github.com/microsoft/prompt-engine)
+- [Prompt Generator for OpenAI's DALL-E 2](http://dalle2-prompt-generator.s3-website-us-west-2.amazonaws.com)
+- [Promptable](https://promptable.ai)
+- [PromptInject](https://github.com/agencyenterprise/PromptInject)
+- [Prompts.ai](https://github.com/sevazhidkov/prompts-ai)
+- [Promptmetheus](https://promptmetheus.com)
+- [PromptPerfect](https://promptperfect.jina.ai/)
+- [Promptly](https://trypromptly.com/)
+- [PromptSource](https://github.com/bigscience-workshop/promptsource)
+- [Promptist](https://promptist.herokuapp.com/)
+- [Scale SpellBook](https://scale.com/spellbook)
+- [sharegpt](https://sharegpt.com)
+- [ThoughtSource](https://github.com/OpenBioLink/ThoughtSource)
+- [Visual Prompt Builder](https://tools.saxifrage.xyz/prompt)

From afdae4696441d4b2bd96412ad24a06e1ca37f51a Mon Sep 17 00:00:00 2001
From: leochou73 <57980998+leochou73@users.noreply.github.com>
Date: Sun, 9 Apr 2023 11:30:48 +0800
Subject: [PATCH 20/24] Update workplace_casestudy.zh.mdx

---
 pages/applications/workplace_casestudy.zh.mdx | 56 ++++++++++++++++++-
 1 file changed, 54 insertions(+), 2 deletions(-)

diff --git a/pages/applications/workplace_casestudy.zh.mdx b/pages/applications/workplace_casestudy.zh.mdx
index 92e08b7..f8a7666 100644
--- a/pages/applications/workplace_casestudy.zh.mdx
+++ b/pages/applications/workplace_casestudy.zh.mdx
@@ -1,3 +1,55 @@
-# Graduate Job Classification Case Study
+# 毕业生职位分类案例研究
 
-Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
+Clavié等人(2023)提供了一项关于提示工程应用于生产系统中中等规模文本分类用例的案例研究。通过使用将工作分类为真正的“初级职位”(是否适合应届毕业生的任务)，他们评估了一系列提示工程技术，并使用GPT-3.5 (gpt-3.5-turbo)报告了他们的结果。
+
+该研究表明，LLMs在所有经过测试的模型中表现最佳，包括DeBERTa-V3中的一个极强的基准模型。gpt-3.5-turbo在所有关键指标上也明显优于早期的GPT3变体，但需要进行额外的输出解析，因为其遵循模板的能力似乎不如其他变体。
+
+他们的提示工程方法的关键发现是：
+
+- 对于像这样不需要专业知识的任务，Few-shot CoT提示在所有实验中的表现都不如Zero-shot提示。
+- 提示对于引导正确推理的影响非常巨大。简单地要求模型对给定的工作进行分类会得到65.6的F1分数，而后提示工程模型的F1分数为91.7。
+- 试图强制模型遵循模板会降低所有情况下的性能（这种行为在GPT-4的早期测试中消失，这项测试在该论文之后进行）。
+- 许多小的修改对性能产生了巨大的影响。
+  - 下面的表格显示了所有经过测试的修改。
+  - 正确地给出指令并重复关键点似乎是最有效的提升性能的方法。
+  - 简单地给模型一个(人类的)名字并这样称呼它，可以将F1分数提高0.6个百分点。
+
+### 经本文测试的 Prompt策略
+
+| Short name | Description                                                                |
+|------------|----------------------------------------------------------------------------|
+| Baseline   | 提供一个职位招聘信息并询问它是否适合毕业生。          |
+| CoT        | 在查询之前给出几个准确分类的示例。       |
+| Zero-CoT   | 要求模型一步步推理后再给出答案。      |
+| rawinst    | 通过添加到用户消息中, 来给出有关其角色和任务的说明。   |
+| sysinst    | 作为系统消息给出有关其角色和任务的说明。           |
+| bothinst   | 将角色作为系统消息和任务作为用户消息拆分说明。       |
+| mock       | 通过模拟讨论来给出任务说明，其中模型确认了它们。 |
+| reit       | 通过重复强调关键要素来加强说明。              |
+| strict     | 要求模型严格按照给定模板回答。         |
+| loose      |  要求仅根据给定模板给出最终答案。       |
+| right      | 要求模型得出正确的结论。                              |
+| info       |提供额外的信息以解决常见的推理失败。       |
+| name       |  为模型取一个我们在对话中称呼它的名称。              |
+| pos        | 在查询之前向模型提供正面反馈。              |
+
+### 所有Prompt性能策略对性能的影响
+
+|                                        | Precision     | Recall        | F1            | Template Stickiness    |
+|----------------------------------------|---------------|---------------|---------------|------------------------|
+| _Baseline_                             | _61.2_        | _70.6_        | _65.6_        | _79%_                  |
+| _CoT_                                  | _72.6_        | _85.1_        | _78.4_        | _87%_                  |
+| _Zero-CoT_                             | _75.5_        | _88.3_        | _81.4_        | _65%_                  |
+| _+rawinst_                             | _80_          | _92.4_        | _85.8_        | _68%_                  |
+| _+sysinst_                             | _77.7_        | _90.9_        | _83.8_        | _69%_                  |
+| _+bothinst_                            | _81.9_        | _93.9_        | _87.5_        | _71%_                  |
+| +bothinst+mock                         | 83.3          | 95.1          | 88.8          | 74%                    |
+| +bothinst+mock+reit                    | 83.8          | 95.5          | 89.3          | 75%                    |
+| _+bothinst+mock+reit+strict_           | _79.9_        | _93.7_        | _86.3_        | _**98%**_              |
+| _+bothinst+mock+reit+loose_            | _80.5_        | _94.8_        | _87.1_        | _95%_                  |
+| +bothinst+mock+reit+right              | 84            | 95.9          | 89.6          | 77%                    |
+| +bothinst+mock+reit+right+info         | 84.9          | 96.5          | 90.3          | 77%                    |
+| +bothinst+mock+reit+right+info+name    | 85.7          | 96.8          | 90.9          | 79%                    |
+| +bothinst+mock+reit+right+info+name+pos| **86.9**      | **97**        | **91.7**      | 81%                    |
+
+“Template stickiness” 指的是模型多频繁地按照所期望的格式作答。

From c0ace7c2416a2a58d4213bb00f87a870ba3b6b2d Mon Sep 17 00:00:00 2001
From: Jeremy Zucker <djinnome@gmail.com>
Date: Sun, 9 Apr 2023 13:47:10 -0400
Subject: [PATCH 21/24] Update ape.en.mdx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Automatic Prompt Engineer paper claims that this prompt elicits better results:

"Let’s work this out **in** a step by step **way** to be sure we have the right answer."

But the prompt in the ape.en.mdx file misquotes the prompt:

"Let’s work this out **it** a step by step to be sure we have the right answer."
---
 pages/techniques/ape.en.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/techniques/ape.en.mdx b/pages/techniques/ape.en.mdx
index dfe144f..b6086b6 100644
--- a/pages/techniques/ape.en.mdx
+++ b/pages/techniques/ape.en.mdx
@@ -14,7 +14,7 @@ The first step involves a large language model (as an inference model) that is g
 
 APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
 
-The prompt "Let's work this out it a step by step to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
+The prompt "Let’s work this out in a step by step way to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
 
 <Screenshot src={APECOT} alt="APECOT" />
 Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)
@@ -23,4 +23,4 @@ This paper touches on an important topic related to prompt engineering which is
 
 - [AutoPrompt](https://arxiv.org/abs/2010.15980) - proposes an approach to automatically create prompts for a diverse set of tasks based on gradient-guided search.
 - [Prefix Tuning](https://arxiv.org/abs/2101.00190) - a lightweight alternative to fine-tuning that prepends a trainable continuous prefix for NLG tasks. 
-- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - proposes a mechanism for learning soft prompts through backpropagation.
\ No newline at end of file
+- [Prompt Tuning](https://arxiv.org/abs/2104.08691) - proposes a mechanism for learning soft prompts through backpropagation.

From e37798a50c00d89242d744d9c83fba09b98e2e15 Mon Sep 17 00:00:00 2001
From: Jeremy Zucker <djinnome@gmail.com>
Date: Sun, 9 Apr 2023 13:54:50 -0400
Subject: [PATCH 22/24] Update ape.en.mdx

The single-quote was in unicode, so I changed it to ascii for greater compatibility across browsers.
---
 pages/techniques/ape.en.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pages/techniques/ape.en.mdx b/pages/techniques/ape.en.mdx
index b6086b6..e613e66 100644
--- a/pages/techniques/ape.en.mdx
+++ b/pages/techniques/ape.en.mdx
@@ -14,7 +14,7 @@ The first step involves a large language model (as an inference model) that is g
 
 APE discovers a better zero-shot CoT prompt than the human engineered "Let's think step by step" prompt ([Kojima et al., 2022](https://arxiv.org/abs/2205.11916)).
 
-The prompt "Let’s work this out in a step by step way to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
+The prompt "Let's work this out in a step by step way to be sure we have the right answer." elicits chain-of-though reasoning and improves performance on the MultiArith and GSM8K benchmarks:
 
 <Screenshot src={APECOT} alt="APECOT" />
 Image Source: [Zhou et al., (2022)](https://arxiv.org/abs/2211.01910)

From 61b36aa9f21d755909c71219484ef661497f5c58 Mon Sep 17 00:00:00 2001
From: Elvis Saravia <ellfae@gmail.com>
Date: Sun, 9 Apr 2023 19:50:48 -0600
Subject: [PATCH 23/24] add papers

---
 pages/models/chatgpt.en.mdx | 4 ++++
 pages/models/gpt-4.en.mdx   | 4 +++-
 pages/papers.en.mdx         | 6 +++++-
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/pages/models/chatgpt.en.mdx b/pages/models/chatgpt.en.mdx
index ecbe6de..350f443 100644
--- a/pages/models/chatgpt.en.mdx
+++ b/pages/models/chatgpt.en.mdx
@@ -145,6 +145,10 @@ The current recommendation for `gpt-3.5-turbo-0301` is to add instructions in th
 ---
 ## References
 
+- [Large language models can rate news outlet credibility](https://arxiv.org/abs/2304.00228) (April 2023)
+- [Can AI Chatbots Pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) Structural Exams?](https://arxiv.org/abs/2303.18149) (April 2023)
+- [Can AI Put Gamma-Ray Astrophysicists Out of a Job?](https://arxiv.org/abs/2303.17853) (March 2023)
+- [Comparing Abstractive Summaries Generated by ChatGPT to Real Summaries Through Blinded Reviewers and Text Classification Algorithms](https://arxiv.org/abs/2303.17650) (March 2023)
 - [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace](https://arxiv.org/abs/2303.17580) (March 2023)
 - [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://arxiv.org/abs/2303.17395) (March 2023)
 - [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://arxiv.org/abs/2303.17466) (March 2023)
diff --git a/pages/models/gpt-4.en.mdx b/pages/models/gpt-4.en.mdx
index 90433a5..0ec244d 100644
--- a/pages/models/gpt-4.en.mdx
+++ b/pages/models/gpt-4.en.mdx
@@ -158,8 +158,10 @@ We will summarize many applications of GPT-4 in the coming weeks. In the meantim
 ## Library Usage
 Coming soon!
 
-## References
+## References / Papers
 
+- [Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations](https://arxiv.org/abs/2303.18027) (April 2023)
+- [Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text]() (March 2023)
 - [Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams](https://arxiv.org/abs/2303.17003) (March 2023)
 - [GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment](https://arxiv.org/abs/2303.16634) (March 2023)
 - [Humans in Humans Out: On GPT Converging Toward Common Sense in both Success and Failure](https://arxiv.org/abs/2303.17276) (March 2023)
diff --git a/pages/papers.en.mdx b/pages/papers.en.mdx
index 06fdb35..2fe58a0 100644
--- a/pages/papers.en.mdx
+++ b/pages/papers.en.mdx
@@ -4,7 +4,8 @@ The following are the latest papers (sorted by release date) on prompt engineeri
 
 ## Overviews
 
-  - [Nature Language Reasoning, A Survey](https://arxiv.org/abs/2303.14725) (March 2023)
+  - [A Survey of Large Language Models](https://arxiv.org/abs/2303.18223) (April 2023)
+  - [Nature Language Reasoning, A Survey](https://arxiv.org/abs/2303.14725) (Mar 2023)
   - [Augmented Language Models: a Survey](https://arxiv.org/abs/2302.07842) (Feb 2023)
   - [A Survey for In-context Learning](https://arxiv.org/abs/2301.00234) (Dec 2022)
   - [Towards Reasoning in Large Language Models: A Survey](https://arxiv.org/abs/2212.10403) (Dec 2022)
@@ -15,6 +16,7 @@ The following are the latest papers (sorted by release date) on prompt engineeri
 
 ## Approaches
   
+  - [CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society](https://arxiv.org/abs/2303.17760) (Mar 2023)
   - [Self-Refine: Iterative Refinement with Self-Feedback](https://arxiv.org/abs/2303.17651v1) (Mar 2023)
   - [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://arxiv.org/abs/2303.13824) (Mar 2023)
   - [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://arxiv.org/abs/2303.13283) (Mar 2023)
@@ -119,6 +121,8 @@ The following are the latest papers (sorted by release date) on prompt engineeri
 
 ## Applications
   
+  - [Assessing Language Model Deployment with Risk Cards]() (April 2023)
+  - [Enhancing Large Language Models with Climate Resources](https://arxiv.org/abs/2304.00116) (March 2023)
   - [BloombergGPT: A Large Language Model for Finance](https://arxiv.org/abs/2303.17564) (March 2023)
   - [Medical Intervention Duration Estimation Using Language-enhanced Transformer Encoder with Medical Prompts](https://arxiv.org/abs/2303.17408) (March 2023)
   - [Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes](https://arxiv.org/abs/2303.15846) (March 2023)

From ec0addf8dec5429bd4d982a93783082afa3be07c Mon Sep 17 00:00:00 2001
From: Elvis Saravia <ellfae@gmail.com>
Date: Sun, 9 Apr 2023 20:39:15 -0600
Subject: [PATCH 24/24] tr

---
 next.config.js              |  2 +-
 pages/_meta.tr.json         | 28 ++++++++++++++++++++++++++++
 pages/models/chatgpt.tr.mdx |  3 +++
 theme.config.tsx            |  1 +
 4 files changed, 33 insertions(+), 1 deletion(-)
 create mode 100644 pages/_meta.tr.json
 create mode 100644 pages/models/chatgpt.tr.mdx

diff --git a/next.config.js b/next.config.js
index fc40fb6..0b6df8b 100644
--- a/next.config.js
+++ b/next.config.js
@@ -5,7 +5,7 @@ const withNextra = require('nextra')({
 
 module.exports = withNextra({
   i18n: {
-    locales: ['en', 'zh', 'jp', 'pt'],
+    locales: ['en', 'zh', 'jp', 'pt', 'tr'],
     defaultLocale: 'en'
   }
 })
diff --git a/pages/_meta.tr.json b/pages/_meta.tr.json
new file mode 100644
index 0000000..b94eca7
--- /dev/null
+++ b/pages/_meta.tr.json
@@ -0,0 +1,28 @@
+{
+    "index": "Prompt Engineering",
+    "introduction": "Introduction",
+    "techniques": "Techniques",
+    "applications": "Applications",
+    "models": "Models",
+    "risks": "Risks & Misuses",
+    "papers": "Papers",
+    "tools": "Tools",
+    "notebooks": "Notebooks",
+    "datasets": "Datasets",
+    "readings": "Additional Readings",
+    "about": {
+      "title": "About",
+      "type": "page"
+    },
+    "course":{
+      "title": "Prompt Engineering Course",
+      "type": "page"
+    },
+    "contact": {
+      "title": "Contact ↗",
+      "type": "page",
+      "href": "https://twitter.com/dair_ai",
+      "newWindow": true
+    }
+  }
+  
\ No newline at end of file
diff --git a/pages/models/chatgpt.tr.mdx b/pages/models/chatgpt.tr.mdx
new file mode 100644
index 0000000..9e3a7e2
--- /dev/null
+++ b/pages/models/chatgpt.tr.mdx
@@ -0,0 +1,3 @@
+# ChatGPT Prompt Engineering
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/theme.config.tsx b/theme.config.tsx
index 9d699de..16d0aa9 100644
--- a/theme.config.tsx
+++ b/theme.config.tsx
@@ -20,6 +20,7 @@ const config: DocsThemeConfig = {
     { locale: 'zh', text: '中文' },
     { locale: 'jp', text: '日本語'},
     { locale: 'pt', text: 'Português' },
+    { locale: 'tr', text: 'Türkçe' },
   ],
   head: function UseHead() {
     const { title } = useConfig()