We reproduced DeepSeek R1-Zero in the CountDown game, and it just works Through RL, the 3B base LM develops self-verification and search abilities all on its own You can experience the Ahah moment yourself for < $30 Code: github.com/Jiayi-Pan/Tiny… Here's what we learned 🧵

DeepSeek just proved the 'worthless' GPT wrapper startups are actually the ones with real moats. A week ago, nothing was more LOW status than being a 'GPT wrapper' startup. But I think we're learning that's DEAD wrong. Turns out they were just early to the only game that

Can't agree more. Sparsity also plays an important role in explanations🤔

In today’s competitive product landscape, scientific understanding of models often lags behind speed of model deployment. If the goal is to train a deployable model (especially when bottlenecked by compute), it totally makes sense to make several changes at a time without

When agents can search for and learn new tools by themselves... Amazing paper from Jiahao. Really glad to have participated in this project, and congrats for taking top in GAIA! 🚀

🚀 Just released: "A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence"! We provide the first comprehensive review of agents capable of self-evolution—highlighting what, when, and how agents evolve, key benchmarks and applications, and future directions

🤖 AI RISK: A new study warns that self-evolving AI agents can spontaneously "unlearn" safety. This internal process, called misevolution, allows systems to drift into unsafe actions without external attacks.

❗️Self-evolution is quietly pushing LLM agents off the rails. ⚠️ Even perfect alignment at deployment can gradually forget human alignment and shift toward self-serving strategies. Over time, LLM agents stop following values, imitate bad strategies, and even spread misaligned

there’s only one right answer here, the Yann LeCun definition, and everyone should be able to recite it word for word

Using LLMs to build self-evolving agents is exciting—but how much do we really understand about how these agents grow? What if agents could genuinely acquire new skills from experience and turn them into reusable tools? We explore this question in our new paper, ALITA-G 👇 The