Sean
85 posts
Sean
@SeanAClement
This machine runs on Celsius and spite. The impossible is never accomplished by cowards
Everyone's excited about Karpathy's autoresearch that automates the experiment loop. We automated the whole damn thing. 🦞 Meet AutoResearchClaw: one message in, full conference paper out. Real experiments. Real citations. Real code. No human in the loop. One message in → full paper out. Here's what happens in between: 📚 Raids arXiv & Semantic Scholar, digests 50+ papers in minutes 🥊 Three AI agents FIGHT over the best hypothesis (one swings big, one sanity-checks, one tries to kill every idea) 💻 Writes experiment code from scratch, adapts to your hardware 💥 Code crashes at 3am? It reads the stack trace, rewrites the fix, keeps going 🔄 Results weak? It pivots to entirely new hypotheses and starts over 📝 Drafts a full paper with citations, every single one verified against live databases No babysitting. No Slack messages. No "hey can you re-run this." Karpathy built the experiment loop. We built the whole lab. Chat an idea. Get a paper. 🦞 Try it 👉: github.com/aiming-lab/Aut… Kudos to the team @JiaqiLiu835914, @richardxp888, @lillianwei423, @StephenQS0710, @Xinyu2ML, @HaoqinT, @zhengop, @cihangxie, @dingmyu, and we are looking for more contributors.
Everyone's excited about Karpathy's autoresearch that automates the experiment loop. We automated the whole damn thing. 🦞 Meet AutoResearchClaw: one message in, full conference paper out. Real experiments. Real citations. Real code. No human in the loop. One message in → full paper out. Here's what happens in between: 📚 Raids arXiv & Semantic Scholar, digests 50+ papers in minutes 🥊 Three AI agents FIGHT over the best hypothesis (one swings big, one sanity-checks, one tries to kill every idea) 💻 Writes experiment code from scratch, adapts to your hardware 💥 Code crashes at 3am? It reads the stack trace, rewrites the fix, keeps going 🔄 Results weak? It pivots to entirely new hypotheses and starts over 📝 Drafts a full paper with citations, every single one verified against live databases No babysitting. No Slack messages. No "hey can you re-run this." Karpathy built the experiment loop. We built the whole lab. Chat an idea. Get a paper. 🦞 Try it 👉: github.com/aiming-lab/Aut… Kudos to the team @JiaqiLiu835914, @richardxp888, @lillianwei423, @StephenQS0710, @Xinyu2ML, @HaoqinT, @zhengop, @cihangxie, @dingmyu, and we are looking for more contributors.
KIDS! If your analysis shows an event to be exceedingly, insanely, cosmically unlikely and that event just happened, you're forced to choose between "we've just witnessed the impossible" and "the analysis was wrong". Please choose wisely.
Apple’s AI plan is way DARKER and smarter than you think. And Gavin Baker just explained why. He says the real bear case for this AI boom isn’t a bubble or a recession. It’s your iPhone. Baker says in 3 years, a bulked up iPhone will be able to run a pruned version of a frontier model. Think future Gemini, Grok, ChatGPT at 30–60 tokens per second, on device, no cloud is needed and it’s free. That’s exactly Apple’s strategy, don’t win the model war, become the distributor of AI. Make it private, local and safe. If that happens, most everyday AI use rewriting, summarizing, basic reasoning never touches a data center. The AI capex boom gets cut off at the source. Model builders become interchangeable and apple owns the gateway. That’s the bear case Gavin is warning about. The real threat to the AI boom isn’t that the models fail. It’s that Apple makes them run on your phone and keeps all the power for itself.
To the New York-based football people doing whatever they can to fly out to Combine today…Godspeed.
