Want to create an interactive transcript for this episode?
Podcast: TYPE III AUDIO (All episodes)
Episode: [Week 2] "Learning from human preferences" (Blog Post) by Dario Amodei, Paul Christiano & Alex Ray
Description: ---client: agi_sfproject_id: core_readingsfeed_id: agi_sf__alignmentnarrator: pwqa: mdsqa_time: 0h15m---One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is b...