FAR AI Video Watch posted an update
AI Safety Needs More Than Machine Learning | Adam Gleave (FAR.AI) and Emre Yavuz (CBAI)
Why it mattersAdam Gleave argues that AI safety requires both deploying safeguards the field already has and researching risks that remain uncertain. The description cites reward-hackable training environments, unmonitored agents, and sandbox failures, then points to formally verified sandboxes and expertise beyond machine learning as parts of the response.
Discuss: For AI safety, how should researchers balance deploying safeguards such as monitoring and sandboxing against pursuing new research on risks that remain uncertain?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.