Prometheus

Retroactive Funding for Alignment
by Prometheus @ 2025-10-25 | +18 | 0 comments

Back to the Past to the Future
by Prometheus @ 2023-10-18 | +4 | 0 comments

Why Is No One Trying To Align Profit Incentives With Alignment Research?
by Prometheus @ 2023-08-23 | +17 | 0 comments

Slaying the Hydra: toward a new game board for AI
by Prometheus @ 2023-06-23 | +3 | 0 comments

Lightning Post: Things people in AI Safety should stop talking about
by Prometheus @ 2023-06-20 | +5 | 0 comments

Aligned Objectives Prize Competition
by Prometheus @ 2023-06-15 | +8 | 0 comments

AI Safety Strategy - A new organization for better timelines
by Prometheus @ 2023-06-14 | +8 | 0 comments

Prometheus's Quick takes
by Prometheus @ 2023-06-13 | +3 | 0 comments

Using Consensus Mechanisms as an approach to Alignment
by Prometheus @ 2023-06-11 | +14 | 0 comments

Humans are not prepared to operate outside their moral training distribution
by Prometheus @ 2023-04-10 | +12 | 0 comments

Widening Overton Window - Open Thread
by Prometheus @ 2023-03-31 | +12 | 0 comments

4 Key Assumptions in AI Safety
by Prometheus @ 2022-11-07 | +5 | 0 comments

Five Areas I Wish EAs Gave More Focus
by Prometheus @ 2022-10-27 | +8 | 0 comments