AI tricks - Revision history

KevinYager: /* Prompt Engineering */

2026-01-12T15:04:40Z

‎Prompt Engineering

2025-10-13T19:37:02Z

‎Prompt Engineering

2025-08-11T19:07:41Z

‎Prompt Engineering

2025-08-07T15:22:38Z

‎Position Bias

2025-08-01T16:56:16Z

‎Prompt Engineering

2025-07-18T16:53:09Z

‎Prompt Engineering

2025-07-07T13:09:27Z

‎Prompt Engineering

2025-06-11T15:24:04Z

‎Prompt Engineering

2025-06-08T15:16:51Z

‎Chain of Thought (CoT)

2025-05-08T12:16:16Z

‎Position Bias

@@ Line 7: / Line 7: @@
 * 2025-08: OpenAI: [https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide GPT-5 prompting guide]
 * 2025-10: [https://arxiv.org/abs/2510.04950?ref=blog.anyreach.ai Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy]
 ==In-Context Learning==

@@ Line 6: / Line 6: @@
 * 2025-08: [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5375404 Prompting Science Report 3: I'll pay you or I'll kill you -but will you care?]
 * 2025-08: OpenAI: [https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide GPT-5 prompting guide]
 ==In-Context Learning==

@@ Line 5: / Line 5: @@
 * 2025-07: [https://arxiv.org/abs/2507.13334 A Survey of Context Engineering for Large Language Models]
 * 2025-08: [https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5375404 Prompting Science Report 3: I'll pay you or I'll kill you -but will you care?]
 ==In-Context Learning==

@@ Line 33: / Line 33: @@
 * 2024-11: [https://arxiv.org/abs/2411.01101 Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems]
 * 2025-02: [https://arxiv.org/abs/2502.01951 On the Emergence of Position Bias in Transformers]
 * '''Testing models:'''
 ** [https://github.com/gkamradt/LLMTest_NeedleInAHaystack?utm_source=chatgpt.com Needle-in-a-Haystack tests]

@@ Line 4: / Line 4: @@
 * 2025-06: [https://arxiv.org/abs/2506.05614 Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks]
 * 2025-07: [https://arxiv.org/abs/2507.13334 A Survey of Context Engineering for Large Language Models]
 ==In-Context Learning==

@@ Line 24: / Line 24: @@
 * 2024-11: [https://arxiv.org/abs/2411.10541 Does Prompt Formatting Have Any Impact on LLM Performance?]
-==Position Bias==
+==Brittleness==
 * 2023-07: [https://arxiv.org/abs/2307.03172 Lost in the Middle: How Language Models Use Long Contexts]
 * 2024-11: [https://arxiv.org/abs/2411.01101 Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems]

@@ Line 2: / Line 2: @@
 * 2025-03: [https://arxiv.org/abs/2503.04818 Prompting Science Report 1: Prompt Engineering is Complicated and Contingent]
 * 2024-06: [https://arxiv.org/abs/2406.06608 The Prompt Report: A Systematic Survey of Prompting Techniques]
 ==In-Context Learning==

@@ Line 8: / Line 8: @@
 ==Chain of Thought (CoT)==
-"Let's think step-by-step"
+* 2022-05: [https://arxiv.org/abs/2205.11916 Large Language Models are Zero-Shot Reasoners] "Let's think step-by-step"
-* [https://arxiv.org/abs/2406.07496 TextGrad: Automatic "Differentiation" via Text]
+* 2024-06: [https://arxiv.org/abs/2406.07496 TextGrad: Automatic "Differentiation" via Text]
 ==Multi-step==

@@ Line 26: / Line 26: @@
 * 2024-11: [https://arxiv.org/abs/2411.01101 Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems]
 * 2025-02: [https://arxiv.org/abs/2502.01951 On the Emergence of Position Bias in Transformers]
-* ''Testing models:''
+* '''Testing models:'''
 ** [https://github.com/gkamradt/LLMTest_NeedleInAHaystack?utm_source=chatgpt.com Needle-in-a-Haystack tests]
 ** 2023-08: [https://arxiv.org/abs/2308.14508 LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding]
@@ Line 33: / Line 33: @@
 ** 2024-07: [https://arxiv.org/abs/2407.16695 Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack]
 ** 2025-04: [https://arxiv.org/abs/2504.04150 Reasoning on Multiple Needles In A Haystack]
-* ''Mitigation:''
+* '''Mitigation:'''
 ** 2023-10: [https://arxiv.org/abs/2310.01427 Attention Sorting Combats Recency Bias In Long Context Language Models]
 ** 2024-07: [https://arxiv.org/abs/2407.01100 Eliminating Position Bias of Language Models: A Mechanistic Approach]