Sidestepping Evaluation Awareness and Anticipating Misalignment with Evaluations
(alignment.openai.com)
3 pts|24 days ago|discuss
245 karma | created 4 years ago
3 pts|24 days ago|discuss
27 days ago|discuss
2 months ago|discuss
32 pts|3 months ago|4 comments
2 pts|3 months ago|discuss
3 pts|5 months ago|discuss
5 months ago|discuss
2 pts|5 months ago|1 comment
333 pts|7 months ago|126 comments
1 pts|7 months ago|discuss
2 pts|8 months ago|discuss
2 pts|8 months ago|discuss
2 pts|8 months ago|discuss
17 pts|8 months ago|1 comment
9 months ago|discuss
3 pts|9 months ago|discuss
4 pts|10 months ago|discuss
2 pts|10 months ago|discuss
2 pts|10 months ago|discuss