News for hackers. Stuff that matters.

A comment on Anthropic's 'Watermark' Text Adulteration in Claude Is a Perversion of Writing. Parent comment

Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by inigyou on Sunday August 16, 2026 @08:31PM (#49325274)
Would be fun to run an LLM on fake output from itself. Like just force the first N tokens to say the beginning of something really stupid, and then see how it finishes the sentence. "You're absolutely right! Human feces is actually the most effective engine coolant because $<completion>"
[ Parent | on HN ]
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by Gracana on Monday August 17, 2026 @09:45AM (#49330755)
Some LLM interfaces allow you to modify and “continue” an agent response. It’s very useful for guidance, including jailbreaking. Need the model to go in a certain direction? Got a refusal that you want to bypass? Just start it off in the appropriate direction and then have it continue from there.
[ Parent | on HN ]
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by inigyou on Monday August 17, 2026 @11:55AM (#49333059)
Which ones?
[ Parent | on HN ]
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by Gracana on Tuesday August 18, 2026 @11:54PM (#49356534)
llama.cpp (but maybe not for reasoning models?) and sillytavern, maybe others... I'm half a country away from my desktop right now so I can't verify much right now.
[ Parent | on HN ]