←back to thread

Claude for Chrome

(www.anthropic.com)
795 points davidbarker | 1 comments | 26 Aug 25 19:01 UTC | HN request time: 0.229s | source
Show context
biggestfan ◴[26 Aug 25 19:11 UTC] No.45030868[source]▶
According to their own blog post, even after mitigations, the model still has an 11% attack success rate. There's still no way I would feel comfortable giving this access to my main browser. I'm glad they're sticking to a very limited rollout for now. (Sidenote, why is this page so broken? Almost everything is hidden.)
replies(5): >>45030924 #>>45031456 #>>45031949 #>>45033353 #>>45034111 #
Szpadel ◴[26 Aug 25 20:30 UTC] No.45031949[source]▶
well, at least they are honest about it and don't try to hide it in any way. They probably want to gather more real world data for training and validation, that's why this limited release. openai have browser agent for some time already but I didn't hear about any security considerations. I bet they have the same issues
replies(2): >>45034520 #>>45037881 #
1. latexr ◴[27 Aug 25 10:51 UTC] No.45037881[source]▶
> at least they are honest about it and don't try to hide it in any way.

Seems more likely they’re trying to cover their own ass, so when anything inevitably goes wrong they can point and say “see, we told you it was dangerous, not our fault”.