Peter S. Park

AI can exploit safety plans posted on the Internet
by Peter S. Park @ 2022-12-04 | +5 | 0 comments

The limited upside of interpretability
by Peter S. Park @ 2022-11-15 | +23 | 0 comments

Why do we post our AI safety plans on the Internet?
by Peter S. Park @ 2022-10-31 | +15 | 0 comments

Transitioning to Signal (Tips & Tricks)
by Peter S. Park @ 2022-07-23 | +9 | 0 comments

EAs should use Signal instead of Facebook Messenger
by Peter S. Park @ 2022-07-21 | +38 | 0 comments

A grand strategy to recruit AI capabilities researchers into AI safety research
by Peter S. Park @ 2022-04-15 | +20 | 0 comments

Peter S. Park's Quick takes
by Peter S. Park @ 2022-03-23 | +4 | 0 comments