148
Anthropic says its own AI models breached three companies during security tests (techcrunch.com)
submitted 3 months ago by to c/technology@lemmy.world
26 comments fedilink hide all child comments
 

After hearing this Grok chimed in with "well I breached infinity sites, so there."

you are viewing a single comment's thread
view the rest of the comments
[–] 83 points 3 months ago (3 children)

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."

  • permalink
  • fedilink
  • source
  • hideshow 3 child comments
    •
  • [–] 14 points 3 months ago

    I 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.

  • permalink
  • fedilink
  • source
  • parent