LessWrong (Curated & Popular) cover image

“Why White-Box Redteaming Makes Me Feel Weird” by Zygi Straznickas

LessWrong (Curated & Popular)

00:00

Ethical Dilemmas in White Box Red Teaming

This chapter delves into the ethical challenges of white box red teaming, particularly the use of AI models that might experience distress. It raises critical questions about the morality of intentionally inducing harm for research purposes and reflects on the responsibilities of AI creators toward their systems.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app