Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought Xiang et al. : https://
arxiv.org/abs/2501.04682 #ArtificialIntelligence #AIAgents
PROMPT ENGINEERING
-
Meta Chain-of-Thought: Teaching LLMs Advanced Reasoning
By
–
-
Meta Chain-of-Thought: Teaching LLMs Advanced Reasoning
By
–
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought Xiang et al.: https://
arxiv.org/abs/2501.04682 #ArtificialIntelligence #AIAgents -
Karpathy’s LLM Insights Turned Into Claude Code Config Fix
By
–
Karpathy's X thread about LLM failures is now a config file fixing Claude Code. Claude Code has a well-known problem. It over-explains, adds code you didn't ask for, and forgets your constraints mid-conversation. Andrej Karpathy studied these failures closely. He found
-
Using Feynman-style loops in AI prompting
By
–
Have you tried adding Feynman-style loops to your AI prompts yet? Want me to build a version of this for your field? Let me know in the comments
-
Using LLMs as an expert tutor for accelerated learning
By
–
Here's the prompt that can make you learn anything 10x faster: You are a master explainer who channels Richard Feynman’s ability to break complex ideas into simple, intuitive truths.
Your goal is to help the user understand any topic through analogy, questioning, and -
Designing a Feynman-inspired Meta-Prompt for LLMs
By
–
RICHARD FEYNMAN’S WHOLE LEARNING PHILOSOPHY… PACKED INTO ONE PROMPT I spent days engineering a meta-prompt that teaches you any topic using Feynman’s exact approach: simple analogies, ruthless clarity, iterative refinement, and guided self-explanation. It feels like having a
-
Teaching AI Agents to Understand Your Improvement Goals
By
–
Yeah, AI doesn't quite grok what you are trying to have it improve. Sometimes my agents are similar. So gotta come at it a different way until they "get" it.
-
Practice and Settings for Prompt Optimization Success
By
–
it might just take a bit of practice! give it some time, or send us the prompt + settings so we can duplicate it in our engineering setting <3
-
Midjourney Discontinues V8 Model in Favor of V8.1
By
–
we plan on discontinuing v8 soon, if you have good prompts that show something v8 is doing that v8.1 can't do please let us know. So far it seems like with the right personalization or sref or style refe 8.1 can basically do everything better