RSS

sevdeawesome

Karma: 36

Whirlwind Tour of Chain of Thought Liter­a­ture Rele­vant to Au­tomat­ing Align­ment Re­search.

sevdeawesomeJul 1, 2024, 5:50 AM
25 points
0 comments17 min readLW link

A Re­view of Weak to Strong Gen­er­al­iza­tion [AI Safety Camp]

sevdeawesomeMar 7, 2024, 5:16 PM
13 points
0 comments9 min readLW link