Skip to content
NewA calmer, faster ZeroHour

Academia is for Ambition — Alex Zhang, MIT

Latent Space ()15 min read9 · 7 reads
AI summary · grok-4.7Summaries by Vani AI

MIT's Alex Zhang discusses Recursive Language Models, GPU kernels, and multi-agent harnesses.

Latent Space interviewed MIT PhD Alex Zhang about Recursive Language Models, KernelBench, and multi-agent harnesses. Zhang describes context offloading, code execution, and recursive subagents, noting an RLM-based harness approached ARC-AGI-3 before OpenAI's Astra. The discussion also covers AI-written GPU kernels, OpenAI's reported 10,000-agent experiment, Kimi swarms, and Sakana AI's open-ended research.

Key facts
  • Alex Zhang discusses RLMs that offload context and call recursive subagents.
  • An RLM harness approached ARC-AGI-3 before OpenAI's Astra.
  • AI-written GPU kernels still leave substantial room for human expertise.
  • OpenAI's swarm trial reportedly used about 10,000 agents and 130 billion tokens.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

15 min read at latent.space

We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.