4 - Risks from Learned Optimization with Evan Hubinger

episode

AXRP - the AI X-risk Research Podcast not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

Related

recent transcribed audio

A.I. Safety Goes Mainstream + a ‘Hard Fork’ Exit AMA 1h 25m · 18 Sep 2026 · Hard Fork

Layoffs at the Kansas City Star will hurt local communities 15 min · 18 Sep 2026 · Kansas City Today

AWP: Beyond the Exam Room: Purpose, Myopia, and Population Health 54 min · 17 Sep 2026 · EyeCode Media

Planning Commission Meeting - Sep 17, 2026 1h 11m · 17 Sep 2026 · Leesburg Planning Commission

Heritage Commission - Sep 14, 2026 1h 57m · 17 Sep 2026 · Loudoun County Board Committees and Advisory Boards

Historic District Review Committee - Sep 14, 2026 1h 36m · 17 Sep 2026 · Loudoun County Board Committees and Advisory Boards

Report any issue

Source

Recorded17 Feb 2021

Publisheraxrpodcast.libsyn.com ↗

Handlerec:5638305

Show notes

In machine learning, typically optimization is done to produce a model that performs well according to some metric. Today's episode features Evan Hubinger talking about what happens when the learned model itself is doing optimization in order to perform well, how the goals of the learned model could differ from the goals we used to select the learned model, and what would happen if they did differ. Link to the paper - Risks from Learned Optimization in Advanced Machine Learning Systems: arxiv.org/abs/1906.01820 Link to the transcript: axrp.net/episode/2021/02/17/episode-4-risks-from-learned-optimization-evan-hubinger.html Evan Hubinger's Alignment Forum profile: alignmentforum.org/users/evhub

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in