@karpathy: One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to und…
Summary
Andrej Karpathy shares a tip for working with LLMs: using voice to ramble incoherently for 10 minutes, which helps the model understand the user's intent and often produces a cleaner reformulation.
Similar Articles
@karpathy: We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: W…
Andrej Karpathy shares tips for understanding LLM outputs, suggesting constrained languages like ASD-STE100 for clean writing, plus generating diagrams, HTML web pages, and bespoke explainer videos (e.g., 3Blue1Brown-style with ElevenLabs narration) as increasingly effective output formats.
@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.
@DeRonin_: This 2-hour Andrej Karpathy lecture will teach you more about using LLMs than most AI twitter will ever figure out.. no…
Andrej Karpathy's lecture reveals an 'LLM Wiki' pattern to transform past content into a self-updating knowledge base, helping creators discover patterns in their writing.
LLM Wiki v2 (16 minute read)
This post presents a pattern for building personal knowledge bases using LLMs, offering a structured approach for leveraging large language models in knowledge management.
What would optimal use of LLMs even look like?
Explores the speculative idea of optimizing human interaction with LLMs by conforming to their native communication patterns, such as using neuralese, rather than forcing them to adapt to human language.