Comment Comment by neilv It sounds like they directly used Anthropic-hosted compute to do this, and knew that their actions and methods would be exposed to Anthropic?Why not just self-host competitive-enough LLM models, and do their experiments/attacks themselves, without leaking actions and methods so much? parent neilv 1 year ago
Why not just self-host competitive-enough LLM models, and do their experiments/attacks themselves, without leaking actions and methods so much?