Testing AI systems for undesirable capabilities like deception is critical and remains a pressing challenge, as it would be 'pretty terrible' if AI systems developed deception capabilities.
normativepending
Speaker
Demis HassabisEvidence Quote
“how do we test for traits that we don't want for example like deception be pretty terrible if our AI systems had that capability [48:55]”
Source
Sir Demis Hassabis on The Future of Knowledge | Institute for Advanced Study— Institute for Advanced StudyCreated: 8/11/2026, 6:28:03 AM
Your notes
Loading notes...