4 - Risks from Learned Optimization with Evan Hubinger
AXRP - the AI X-risk Research Podcast
Do You Want to Avoid Mesooptimizers?
One way of avoiding masomisers is to avoid doing things that require modelling humans. So, for instance, natural language processing or natural language prediction where he trying to predict, like, maybe me. There are also ways in which we could train a sort of predictsid model abont yor data. And then tryig to use this model to directly influence the world rather than using it as an extractive agent with transparency tools.
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.
