Press Space to continue
Safety Testing Cannot Detect Internal Lab Compromises
Press Space to continue
Even perfect safety testing couldn’t have caught OpenAI’s Hugging Face hack under the current regime, Apollo Research’s CEO says. The blind spot: labs’ internal use. Read more: https://thein.fo/3VtiQ8c
open on x · 2 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.