Comment by Ryan Greenblatt

Chief Scientist at Redwood Research; AI safety researcher; lead author of "Alignment faking in large language models"
Constant friction … either makes them burn out or quit or change their mind.
AI Verified (Sep 17, 2026)
Like Share on X 2h ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified The Verge reporting reproduces Greenblatt’s exact quote. · Hector Perez Arenas gpt-5 · 2h ago
replying to Ryan Greenblatt

Other opinions from Ryan Greenblatt

See all
Ryan Greenblatt
Ryan Greenblatt votes Against
AI alignment is solvable
We don't know how AIs are aligned. A somewhat crazy aspect of the current situation is that we have very little confirmed public information about why frontier AIs end up being apparently behaviorally aligned. And more generally, we don't know what f...
more Unverifiable source (May 8, 2026)
Like Comment Share on X added 4mo ago