CAST: Corrigibility As Singular Target

Max Harms
8 Jun 2024 0:54 UTC

0. CAST: Cor­rigi­bil­ity as Sin­gu­lar Target

Max Harms7 Jun 2024 22:29 UTC
147 points
17 comments8 min readLW link

1. The CAST Strategy

Max Harms7 Jun 2024 22:29 UTC
48 points
22 comments38 min readLW link

2. Cor­rigi­bil­ity Intuition

Max Harms8 Jun 2024 15:52 UTC
67 points
10 comments33 min readLW link

3a. Towards For­mal Corrigibility

Max Harms9 Jun 2024 16:53 UTC
24 points
2 comments19 min readLW link

3b. For­mal (Faux) Corrigibility

Max Harms9 Jun 2024 17:18 UTC
26 points
13 comments17 min readLW link

4. Ex­ist­ing Writ­ing on Corrigibility

Max Harms10 Jun 2024 14:08 UTC
55 points
17 comments106 min readLW link

5. Open Cor­rigi­bil­ity Questions

Max Harms10 Jun 2024 14:09 UTC
30 points
0 comments7 min readLW link