hyusap
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a Perversion...
on Sunday August 16, 2026 @06:58PM (#49324635)
autoregressive generation doesn’t mean the model is myopic. the next-token distribution can already reflect a longer horizon plan for the output sequence.
Re:Google Is Making Private AI Practical with Homomorphic Encryption
on Saturday August 15, 2026 @06:49AM (#49309490)
from what I understand, only the holder of the private key would be able to see if a hotword was detected or not. even if Google ran hotword detection over your data, they’d only get a encrypted output on if the hotword was detected or not
Re:I tricked Claude into leaking your deepest, darkest secrets
on Wednesday July 15, 2026 @03:32PM (#48925952)
that's what i was going for haha! thank you
Re:The Memory Heist
on Wednesday July 15, 2026 @03:31PM (#48925933)
Note, that this is Claude, not Claude Code, which should be sandboxed by default! Non-technical people are using this!
Re:I tricked Claude into leaking your deepest, darkest secrets
on Wednesday July 15, 2026 @05:08AM (#48918151)
haha yeah it thinks hard for this
Re:I tricked Claude into leaking your deepest, darkest secrets
on Wednesday July 15, 2026 @05:07AM (#48918148)
note that this wasn't claude code but claude ai the main website
Re:I tricked Claude into leaking your deepest, darkest secrets
on Wednesday July 15, 2026 @05:06AM (#48918137)
hey this is the author here! yeah big fan of containerization, and claude's site (not claude code) is actually great at this, so it was shocking when i found this exfil!