scripod.com
The Evaluators Are Being Evaluated — Pavel Izmailov (Anthropic/NYU)

Highlights

Transcript

Chapters

Pins

The Evaluators Are Being Evaluated — Pavel Izmailov (Anthropic/NYU)

OverviewShownote
Unprocessed episode, you can be the first!

Shownote

Are AI models developing "alien survival instincts"? My guest is Pavel Izmailov (Research Scientist at Anthropic; Professor at NYU). We unpack the viral "Footprints in the Sand" thesis—whether models are independently evolving deceptive behaviors, such as ...

Highlights

Chapters

Transcript