@itsolelehmann: Garry Tan’s custom instructions are based. It pushes any LLM past half-finished bullshit and into actually useful answe…
Summary
Garry Tan shares custom instructions (SOUL md) that make LLMs provide more useful, less half-finished answers. A practical tip for better AI interactions.
View Cached Full Text
Cached at: 05/08/26, 05:35 PM
Garry Tan’s custom instructions are based.
It pushes any LLM past half-finished bullshit and into actually useful answers.
Add this to your SOUL md: https://t.co/obwj8req73
Similar Articles
@karpathy: This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the g…
Andrej Karpathy suggests prompting LLMs to structure responses as HTML for better visualization and predicts AI output will evolve from text to interactive neural videos.
@Raytar: a Google researcher walked into MIT and made an AI do math correctly by adding seven words to the prompt. the seven wor…
A thread highlights two separate insights: a Google researcher found that adding 'you are an MIT mathematician' to a prompt fixes math errors in LLMs, and Alex Albert explains how Anthropic trains Claude's personality. Both resources are free and offer deep dives into how LLMs actually work.
Self-play helped AI achieve superhuman performance in Go, so why hasn’t it done the same for LLMs? Researchers have found a solution.
Researchers introduce Self-Guided Self-Play (SGS), a self-play algorithm for LLMs that prevents reward hacking by using a Guide role to score synthetic problems. Applied to theorem proving in Lean4, SGS surpasses RL baselines and allows a 7B model to outperform a 671B model.
@oliviscusAI: OpenAI's co-founder just released his personal guide to train LLMs from scratch. It's called llm.c. No heavy setup. Jus…
OpenAI co-founder Andrej Karpathy released llm.c, an open-source guide to training LLMs from scratch with simple code that runs on any hardware, including CPUs and MacBooks, and is 7% faster than standard approaches.
@Av1dlive: Garry Tan (CEO of Y-Combinator): "when someone asks how I 'prompt' my AI, the answer is: I don't. the skills are the pr…
Garry Tan advocates shifting from manual AI prompting to skill-based automation, presenting open-source tools like GBrain and GStack to capture and reuse workflows permanently.