[Research Log: RLFCV2, Petertodd, the paperclip maximizer](https://www.lesswrong.com/posts/doLkRMasXMKyafJrz/research-log-rlfcv2-training-phi-1-5-gpt2xl-and-falcon-rw-1b) | |
[Research Log: RLFCV2, Petertodd, the paperclip maximizer](https://www.lesswrong.com/posts/doLkRMasXMKyafJrz/research-log-rlfcv2-training-phi-1-5-gpt2xl-and-falcon-rw-1b) | |