Agree I’m having a lot better time with the recent 2.5 models.
@karpathy
-
Critique du classement LMArena : illusion des performances modèles
By
–
There's a new paper circulating looking in detail at LMArena leaderboard: "The Leaderboard Illusion" https://arxiv.org/abs/2504.20879 I first became a bit suspicious when at one point a while back, a Gemini model scored #1 way above the second best, but when I tried to switch for a few
-
Tic Tac Toe Complexity and Benchmark Performance Discussion
By
–
Hey @timzaman can you rerun your bench maybe. Personally btw I think tic tac toe is secretly relatively hard. There are 8 lines to check. Each a medium tricky indexing op. And if you want to play, you have to roll it out a bit. Humans find it easy to play because they use their
-
Beyond Pokémon: AI Systems Struggle with Basic Games
By
–
forget pokemon they can't play tic tac toe, so something deeper and interesting is going on.
-
LLMs Generate Viral Tweets and Naval-Style Content Effectively
By
–
I had the same thought this morning. I tried to ask an LLM to generate tweets that would go viral and it worked pretty well. Or in style of Naval and they all blew my mind in the usual way. Not sure what to make of that. The most valuable skill is not the one that will be
-
AI Assistance Becomes Default in Coding Practices
By
–
haha nice i love that it just rolls the default over. "coding" basically assume AI assistance as the default coding now, legacy coding becomes "handcoding".
-
Finding Better Term for AI Assisted Coding Beyond Vibe Coding
By
–
I inherited "AI assisted coding" from this @simonw post: https://
simonwillison.net/2025/Mar/19/vi
be-coding/
… But I think it needs work. It doesn't roll off the tongue. Few days ago a friend asked me if I was vibe coding and I said no I'm "real coding". Possible candidate 😀 -
AI-Assisted Coding Workflow and Context Management Strategies
By
–
Noticing myself adopting a certain rhythm in AI-assisted coding (i.e. code I actually and professionally care about, contrast to vibe code). 1. Stuff everything relevant into context (this can take a while in big projects. If the project is small enough just stuff everything
-
LLM-First Ergonomics: Rethinking Interface Design for AI
By
–
PSA It’s a new era of ergonomics.
The primary audience of your thing (product, service, library, …) is now an LLM, not a human. LLMs don’t like to navigate, they like to scrape.
LLMs don’t like to see, they like to read.
LLMs don’t like to click, they like to curl. Etc etc. -
Documentation and Products Must Evolve for LLM Interaction
By
–
The docs also have to change in the content. Eg instead of instructing a person to go to some page and do this or that, they could show curl commands to run – actions that are a lot easier for an LLM to carry out. Products have to change to support these too. Eg adding a