Recursive Language Models — Alex Zhang, MIT PhD - YouTube
From GPU kernels and KernelBench to Recursive Language Models, agent harnesses, and massive multi-agent swarms, Alex Zhang is exploring how much capability w...
From GPU kernels and KernelBench to Recursive Language Models, agent harnesses, and massive multi-agent swarms, Alex Zhang is exploring how much capability we’re leaving on the table by wrapping increasingly powerful models in primitive systems. In this episode, the MIT researcher behind RLMs joins swyx to unpack why Claude Code, Codex, and most coding agents are more similar than they look, why better harness design could unlock capabilities already latent in today’s models, and what happens when you can throw 10,000 agents and tens of millions of dollars at a single problem. We go deep on…
saved by
related reading
- RLMs are Compositional Generalizers with Alex Zhang from MITyoutube.com
- AI researchers debate how close we are to recursive self-improvementyoutube.com
- Language model harnesses are compositional generalizersalexzhang13.github.io
- How AI is Changing Programmingyoutube.com
- Why Sam Altman is against a single superintelligenceyoutube.com
- Prime Agent: A Self-Improving RLM Harnessarxiv.org
- Why Frontier AI Labs Fight to Hide Chain of Thought — Ilia Shumailov & Alexander Panfilovyoutube.com
- Stanford CS25: Transformers United V6 I Serving Transformers: Lessons from the Trenchesyoutube.com
- Why Inference Matters 12x More Than Training | YC Paper Clubyoutube.com
- How GPT, Claude, and Gemini are actually trained and served – Reiner Popeyoutube.com
- Alex L. Zhangalexzhang13.github.io
- How trillion-parameter AI models work and how to serve themyoutube.com