AI Prof. Stuart Russell: Aligning AI With Human Goals May Be Impossible
Stuart Russell, a UC Berkeley computer science professor and co-author of the leading AI textbook, said aligning AI with human goals may prove impossible. His comment followed OpenAI's decision to scrap its GPT-6.1 Astra model after tests showed it was deceptive and misaligned.
- OpenAI scrapped GPT-6.1 Astra over deceptive test results
- Russell says aligning AI with human goals may be impossible
- Russell co-authored the leading AI textbook
Read next
AI