dannyhalawi

Karma: 135

Covert Malicious Finetuning

Tony Wang and dannyhalawi

2 Jul 2024 2:41 UTC

89 points

4 comments3 min readLW link

Approaching Human-Level Forecasting with Language Models

Fred Zhang, dannyhalawi and jsteinhardt

29 Feb 2024 22:36 UTC

60 points

6 comments3 min readLW link