Actually I feel the same way btw. It feels a little bit irrational (?) but real. It's some (illusion?) or degree of control and some degree of interpretability of what is happening when I press go.
@karpathy
-
LLM Conversation Strategies: New Chats vs Persistent Memory
By
–
When working with LLMs I am used to starting "New Conversation" for each request. But there is also the polar opposite approach of keeping one giant conversation going forever. The standard approach can still choose to use a Memory tool to write things down in between
-
Appreciation for ChatGPT Deep Research capabilities and summaries
By
–
Ty ChatGPT Deep Research for good summary and pointers, for these reasons – https://
chatgpt.com/share/67da04d8
-558c-8007-bd4f-1ab639d2b5a9
… -
Information Locked in Human-Focused Formats Challenges Codebase Collation
By
–
Codebases are programmatically ~easy to collate into a single file. The issue is that most information is (tragically) locked in formats that were intended for uniquely human consumption – web pages, PDF files, images, videos, audio, etc. pre-LLM era tech.
-
Content Must Adapt: LLMs Will Dominate Attention Over Humans
By
–
It's 2025 and most content is still written for humans instead of LLMs. 99.9% of attention is about to be LLM attention, not human attention. E.g. 99% of libraries still have docs that basically render to some pretty .html static pages assuming a human will click through them.
-
Evaluation Crisis: MMLU Obsolete, Need Better AI Metrics
By
–
My reaction is that there is an evaluation crisis. I don't really know what metrics to look at right now. MMLU was a good and useful for a few years but that's long over.
SWE-Bench Verified (real, practical, verified problems) I really like and is great but itself too narrow. -
Five Years of LLM Improvements Ahead Without Further Progress
By
–
Good highlights! I imagine there’s still many other creative, useful ideas and quality of life improvements. Even if all LLM progress was to stop today I feel like we’d still have like 5 years of these to really get through, internalize and spread.
-
Vibe Coding: A Random Walk Through App Hallucinations
By
–
Haha so it’s like vibe coding but giving up any pretense of control. A random walk through space of app hallucinations.
-
Claude 3.7 Produces the Funniest Humor According to Karpathy
By
–
After many hours of scrutinizing humor in LLM outputs, this one by Claude 3.7 is the funniest by far.
-
GPT-4.5 Mistake: Outdated Dial-Up Computing Trope Criticism
By
–
One really bad mistake that bugs me is in the GPT4 vs 4.5 conversation (the one generated by 4.5), 4.5 asks "still buffering your responses like it's dial-up internet?". This is really bad because it clearly borrows tropes from early days computing, where an older computer is