This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Jered Sutton
j9n.dev
did:plc:omlwdlbtb34qlsq4pnz2eoh7
A fascinating paper by the Anthropic team explores how LLMs can be 'trained' to appear normal during training, only to manifest malicious behavior once deployed.
https://arxiv.org/abs/2401.05566
2024-02-27T18:04:47.389Z