Tim Shi: capable AI models need know-your-user processes against hacking

agihouse_org · x · 2026-11-21

Part 7 of AGI House's thread: on safety, Recursive co-founder Tim Shi focuses on near-term risks like AI-assisted hacking, argues very capable models need a know-your-user process, and suggests alignment research itself can be automated.

Related event: Tim Shi: AI Task Length Doubles Every Few Months; Strong Models Need KYU(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →