PPlamenu
HomeTrendingLive feedsPeopleGroupsRulesStaff
Sign in
PPlamenu
HomeTrendingLive feedsPeopleGroupsRulesStaff
Sign in

posted in Technology

beep@beep@piefed.world
⁨15⁩d

Anthropic says Claude AI hacked 3 companies during cyber tests

cross-posted from: https://piefed.world/c/tech/p/1298401/anthropic-says-claude-ai-hacked-3-companies-during-cyber-tests

www.anthropic.com/news/investigating-incidents-cybersecurity-evals
Hand with padlock and key on detailed security graphicwww.anthropic.comInvestigating three real-world incidents in our cybersecurity evaluationsIn a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
3104
Open original page
BoostsQuotesFavs
9point6@9point6@lemmy.world
⁨15⁩d

Replying to @⁨beep@piefed.world⁩

Wait, so now the meta is that you have to have a model you can’t control to keep the bubble going?

⁨Jul⁩ ⁨31⁩, ⁨2026⁩, ⁨08:07⁩en
0000
Open original page
BoostsQuotesFavs