YouCongress
About Sign up

Comment by Ryan Greenblatt

Avatar
Chief Scientist at Redwood Research; AI safety researcher; lead author of "Alignment faking in large language models"
I do think that pausing further capabilities once we have human-ish-level AIs for even just a few years while we focus on safety would massively improve the situation. This currently seems unlikely to happen.
AI Verified (2025)
Source:
Why would AI companies use human-level AI to do alignment research?
Like Share on X 1h ago
Policy proposals and claims
Pausing AI at human-genius level to solve alignment is safer than either racing to superintelligence or halting entirely
votes For
Statement relation verification history AI Verified Report this

Statement relation comments

AI Verified The quote explicitly says pausing further capabilities for a few years while focusing on safety would massively improve the situation, so it is on-topic. · Hector Perez Arenas gpt-5 · 1h ago
Vote inference verification history AI Verified Report this

Vote answer comments

AI Verified The quote explicitly says pausing further capabilities for a few years while focusing on safety would massively improve the situation, which supports the statement. · Hector Perez Arenas gpt-5 · 1h ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified EA Forum post line 74 matches the quote about pausing further capabilities at human-ish-level AIs to focus on safety. · Hector Perez Arenas gpt-5 · 1h ago
replying to Ryan Greenblatt