
7 - Side Effects with Victoria Krakovna
AXRP - the AI X-risk Research Podcast
Is Your Research Having Negative Consequences?
One possible bad outcome is like a false sense of security. Victoria would also like to mention that if we don't manage to eliminate the interference incentive, then the agent may have an incentive to keep it stable and prevent humans from eliminating options. There might be other issues that we haven't thought of that this kind of auxiliary reward could introduce, that tik wouldn't be there otherwise.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.