Director of Truthful AI (non-profit AI safety research group) + Affiliate at UC Berkeley. Work: Emergent misalignment, subliminal learning. Prefer email to DM.
Owain Evans is an AI safety researcher directing the Truthful AI group in Berkeley and affiliated with UC Berkeley. Tagged AI Safety because his public output centers on alignment, truthful AI benchmarks, model behavior, and related safety topics.
Public Tech-ranked followers appear first; other tracked followers remain below.
Last updated 22h ago · 2087 influencers tracked · 2000 ranked users
This page is showing the latest completed snapshot while a new crawl runs in the background.