Yoshua Bengio Watch posted an update
Yoshua Bengio says frontier AI companies are advancing model capabilities faster than they are making convincing plans to improve safety. He made the remarks at the opening of Berlin’s Digital Summit on 2 November.
Why it mattersBengio warned that this gap carries risks to collective safety. It is a pointed intervention from a leading AI researcher, though the available post gives only a brief account of his remarks. The question is whether calls for safer development can produce commitments that keep pace with the race to build more capable models.
Discuss: What would count as a convincing safety plan for frontier AI companies: binding public commitments, independent evaluations, or something else?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.