Salt la conținut
Global sound
Security Intelligence Podcast

Security Intelligence Podcast

Oh look. Anthropic’s AI models also broke containment.

· 35 min · Sezonul 1 Episodul 45

Note de episod

Last week, OpenAI’s models broke out of their sandboxes to cause chaos. This week, it’s Anthropic’s turn. On this episode of Security Intelligence, Diego Matos Martins, Kimmie Farrington and Jeff Crume join host Matt Kosinski to discuss the results of Anthropic’s internal review of testing procedures following the Hugging Face incident last month. Anthropic uncovered three instances of Claude models escaping containment and hacking real companies during what were supposed to be simulations....

Site: mediacenter.ibm.com

Live, ultima oră: 8.584 melodii pe 3.878 posturi din 126 țări

Descoperă lumea prin radio

Mai multe moduri de a descoperi (9)

Ai auzit ceva frumos? Salvează-l sau deschide-l direct în Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Radio C1 inBluContinuă să asculți