Computerphile

AI Sandbagging

2025 • E20    May 22, 2025    12m
Following the theme of AI research and safety, Aric Floyd talks about how some Large Language Models might follow the all too human trait of sandbagging - "lying" about their true capabilities.

Where to Watch AI Sandbagging

 

  •   
  •   
  •   
  •   
  •   
  •   
  •   

Take Plex everywhere

Watch free anytime, anywhere, on almost any device.
See the full list of supported devices