From Computerphile.

As Large Language Models improve, the tokens they predict form ever more complicated and nuanced outcomes. Rob Miles and Ryan Greenblatt discuss "Alignment Faking" a paper Ryan’s team created – ideas about which Rob made a series of videos on Computerphile in 2017.

The Alignment Faking paper: https://tinyurl.com/C-Paper-AlignmentFaking

Ryan Greenblatt is chief scientist at Redwood Research (a nonprofit AI safety and security research organization): https://tinyurl.com/C-RedwoodResearch

Rob Miled makes videos on AI Safety: https://tinyurl.com/C-RobSKMiles

nb if the video seems a bit ‘smeary’ that’s an artefact of attempting to cancel out the flickering of the light in the background – something I missed while shooting and have done my best to cancel out in the edit. -Sean

Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile

This video was filmed and edited by Sean Riley.

Computerphile is a sister project to Brady Haran’s Numberphile. More at https://www.bradyharanblog.com