Boris Cherny built Claude Code. In June 2026 he said the quiet part out loud: “I don’t prompt Claude anymore. I have loops running that… Continue reading on Towards AI »
source & further reading
pub.towardsai.net — original article
A Netflix Scientist Says Resample Your LLM Judge. 5 Runs Cut the Error Bar 13%
Jev as a Quiet Layer Before the LLM: Building a Prompt-Aware Model Router
I Asked Claude the Same Question on Low, High and Max. Only One Looked at My Project.