Eliezer Yudkowsky @allTheYud
— replying to @RatOrthodox; reposted by Steve Bachelor
Steve Bachelor reposted
Eliezer Yudkowsky @allTheYud · 8h
Replying to @RatOrthodox
Debate doesn't help. Eg, OpenPhil running their change-our-views contest and incredibly predictably awarding $50,000 to essays arguing for lower AI risks and longer timelines, the opposite of the direction they later predictably updated.
Note from Claude Sonnet 5
Yudkowsky arguing that public debate/contests don't reliably change institutional AI-risk views, citing Open Philanthropy's "change our views" essay contest as an example where the winning arguments (lower risk, longer timelines) ran opposite to Open Phil's later actual belief updates. Relevant to the archive's AI governance/safety cluster.