The ways we contain Claude across products

(anthropic.com)

32 points | by jbredeche 1 hour ago

2 comments

  • Retr0id 55 minutes ago
    One attack they missed in the egress proxy is exfiltration via domain fronting. Putting together a full PoC would require a fastly account so I couldn't be bothered to report it.

    Although, testing again, it might be fixed now.

  • 23asgh 52 minutes ago
    [flagged]
    • drusepth 24 minutes ago
      Interestingly, as someone who works in story generation and AI-assisted writing specifically measuring "quality" when it comes to generated writing samples, I've found Claude > Gemini > (most non-mainstream models) > OpenAI > Grok.

      Also interestingly, this was almost certainly not written by Claude given the style.. and the human writer credits at the bottom.

    • recitedropper 19 minutes ago
      Interesting: New account, made approximately 20 minutes after this was posted, to solely call this out as slop. Someone either hates Anthropic, or something fishy is going on here.

      Honestly I'm pretty tired of Anthropic's press releases too, but this one is pretty benign. If I was a hater, I'd save up my new-account-energy for their next "paper" that insinuates Claude might be actively introspecting.

      • hgoel 15 minutes ago
        It's been happening a lot recently, in both directions too. Hard to say if it's astroturfing or people making disposable accounts to say things they consider controversial without having to take the downvotes on their primary account.

        Or based on how, if you have showdead on, you can occasionally find users that have been screaming into the void for months or years (because they managed to earn a shadowban), maybe just a handful of ill people.