News for hackers. Stuff that matters.
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by tomrod on Sunday August 16, 2026 @07:19PM (#49324800)
Isn't this just chain-of-thought though, doing the same thing multiple times without necessarily defining one path?
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by brookst on Sunday August 16, 2026 @07:32PM (#49324884)
Chain of thought attempts to guide a single forward pass.

Reasoning tokens with tool calling tell the model to loop on a one phase of a question and call a tool to indications completion when done.

Related, but not the same thing.