Christopher King comments on GPT-4 aligning with acasual decision theory when instructed to play games, but includes a CDT explanation that’s incorrect if they differ

Christopher King 28 Mar 2023 22:20 UTC
6 points
0
Oh you’re right, it seems to always defect if I fix the typo. Well that’s embarrassing 😅.
What links here?
- GPT-4 aligning with acasual decision theory when instructed to play games, but includes a CDT explanation that’s incorrect if they differ by Christopher King (23 Mar 2023 16:16 UTC; 7 points)