Search: “karpathy”

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many replies are highlighting. But I still think this raises an interesting discussio

I think its easy to say 'Simulation is a new scaling law' and treat it as marketing hyperbole, but midway along this interview you can hear me go from somewhat shitposting to very very serious. I am 2

This AI recursive self improvement (RSI) paper shows no sign of fast takeoff. The AI model advances at about [Intelligence]^0.075, or the the 13th root of input intelligence [1,2]. That means the inte

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (@hyperagentapp) as a reusable s

we built the @hyperspell filesystem around this principle every source in your company feeds into a context graph where we resolve conflicts and assign permissions there’s a filesystem on top of the g

We call ours Operational Language Wiki, essentially a pattern for building memory to fill in the delta between the “dialect” of a team vs the “world language” that the LLM is trained on. Use it to cap

Row-Bot's approach to memory is hybrid. We have taken the best of both worlds. A knowledge graph for the agent + bi-directionaly synced Wiki for human readability/audit. With in-app graph visualizatio

if only vetted institutions (big labs, governments, large enterprises) get unrestricted frontier capability, especially for AI research itself, those players compound their lead while everyone else wo

It's finally out!!! @METR_Evals found that more than half of SWEBench results is unmergeable slop. FrontierCode represents over 1000+ hours of maintainer validated software engineering work most front

Increasingly, HTML Artifacts are becoming a core part of how I work with AI agents. Long-horizon agent sessions need a better way to surface insights about what work it has done. This may not be obvio

Self-improving AI is a big deal! As a first step, I've been exploring how much of the post-training can be automated. Here is a first post on how I am using @FireworksAI_HQ Agent to automate LLM fine-

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and

Instead of predicting text tokens, @si_pbc learns to use a computer from raw screen data, predicting the next mouse movement, click, and keystroke from the pixels in front of it. This is the @Tesla FS

// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in on

Excellent writeup from @willknight who has been following David's work for decades. Also highly recommend @scmallaby's book The Infinity Machine which profiles David's achievements at @GoogleDeepMind

Excited to share some big news: I've joined @FireworksAI_HQ President. I've spent my career at the intersection of great teams, disruptive technology, and massive market opportunity, from architecting

Vibe coders are not going to like this. UC San Diego just published the first real field study of experienced developers using AI agents. They watched 13 of them code in the wild and surveyed 99 more.

I was kicked off the AI Ascent swag committee bc of last year’s “ai a scent” candle nonsense 😂 This year @Alfred_Lin leveled us up. Can’t wait for the aliens to find our AI Ascent 2026 swag one day. “

// Artifacts as Memory Beyond the Agent Boundary // An agent doesn't always need a bigger memory buffer. Sometimes the environment itself remembers on the agent's behalf. New research formalizes this

👇 “I still maintain that LLMs are really dumb and of limited use. it’s my opinion as a practitioner and professional that the hype being peddled by the AI corporations and self promoters (from X grift