Tim Shi: very capable models need a know-your-user process; alignment research can be automated

agihouse_org · x · 2026-11-21

Wrapping up the AGI House thread, Tim Shi focuses on near-term risks like AI-assisted hacking. He argues very capable models need a know-your-user process, and that alignment research itself can be automated too.

Original post →

More from AGI Musings

AGI Musings channel →