Jul 21, 2026 · 43 min · 13 segments
On episode 3 of Lab Notes, Amir Zohrenejad sits down with Qizheng Zhang to explore one of the fastest-moving areas of AI research: recursive self-improvement. Together, they discuss Meta-Harness…
Qizheng ZhangGuest
Amir ZohrenejadHost
[gentle music] It is very difficult for humans to decide ahead of time before an agent starts running what information is important for the agent to finish a specific task.

And I think that is the core reason why I believe you should not manually compress or discard information before you give it to the agent.

But from an agent perspective, maybe in a long-running task, it is somehow valuable at a specific occasion.

Read the full transcript.
Create an account to read the whole episode, search across every transcript, and follow the shows you care about.