James Payor

Karma: 1,120

I think about AI alignment; send help.

I’m also on twitter. More links on my homepage payor.io.

Working through a small tiling result

James Payor13 May 2025 20:28 UTC

66 points

9 comments5 min readLW link

Thinking about maximization and corrigibility

James Payor21 Apr 2023 21:22 UTC

63 points

4 comments5 min readLW link

Some constructions for proof-based cooperation without Löb

James Payor21 Mar 2023 16:12 UTC

43 points

3 comments4 min readLW link

A proof of inner Löb’s theorem

James Payor21 Feb 2023 21:11 UTC

13 points

0 comments2 min readLW link