7 May 2026

11 links · Thursday

agents need control flow, not more prompts

Thesis: reliable agents tackling complex tasks need deterministic control flow encoded in software, not increasingly elaborate prompt chains If you’ve eve...

Why hasn't longer-horizon training slowed AI progress?

Dwarkesh Patel1 recently posted an award for the best answers to four key questions about AI. It’s partly a challenge and partly a job interview, since some of the winners will get offered a role as a “research collaborator”. I don’t want the job, but I do wan…

Programming Still Sucks. — Writing

Sorry Peter. — I'm at a birthday party, and while most people here also work in tech, there's always a Guy with a Real Job. You know, a physical job, building some or other thing people need. And this Guy always asks some variant of the same question: aren't y…