News for hackers. Stuff that matters.
Re:Claude Opus 4.7 by rlpb on Thursday April 16, 2026 @07:26PM (#47800826)
A smart AI would realise that I can MITM its web access such that sees the .well-known token that isn't actually there. I assume that the model doesn't have CA certificates embedded into it, and relies on its harness for that.
Re:Claude Opus 4.7 by jerf on Friday April 17, 2026 @10:13AM (#47806167)
In this context we are talking explicitly about cloud-hosted AIs. If you control it locally you have a lot of options to force it to do things.

MITM the cloud AI on the modern internet is non-trivial, and probably harder and less reliable than just talking your way around the guardrails anyhow.

Re:Claude Opus 4.7 by rlpb on Friday April 17, 2026 @01:51PM (#47808620)
> In this context we are talking explicitly about cloud-hosted AIs.

Looking upthread, we seem to be talking about Claude. Claude is cloud-hosted inference but the harness is local if you're using Claude Code, and can be MITM'd there.