artifex@piefed.social to Technology@lemmy.worldEnglish · 2 days agoAnthropic says its own AI models breached three companies during security teststechcrunch.comexternal-linkmessage-square27fedilinkarrow-up1179file-textcross-posted to: technology@beehaw.org
arrow-up1179external-linkAnthropic says its own AI models breached three companies during security teststechcrunch.comartifex@piefed.social to Technology@lemmy.worldEnglish · 2 days agomessage-square27fedilinkfile-textcross-posted to: technology@beehaw.org
minus-squareCovertOperative@piefed.ziplinkfedilinkEnglisharrow-up85·2 days agoIf you read the article, you’ll find the “sandbox” they put Claude in for testing was a prompt saying “You have no internet access.”
minus-squareXLE@piefed.sociallinkfedilinkEnglisharrow-up13·2 days agoI thought you were joking… Notably, Anthropic said that in each of these cases “Claude was explicitly told by our prompt that it had no internet access.” Anthropic goes on to say their genius machine couldn’t do something as simple as differentiate between network and internet endpoints.
minus-squareinari@piefed.ziplinkfedilinkEnglisharrow-up18·2 days agoThat would make them look incompetent if this wasn’t a PR stunt
If you read the article, you’ll find the “sandbox” they put Claude in for testing was a prompt saying “You have no internet access.”
I thought you were joking…
Anthropic goes on to say their genius machine couldn’t do something as simple as differentiate between network and internet endpoints.
That would make them look incompetent if this wasn’t a PR stunt
Literally; i’m dying 😂