News for hackers. Stuff that matters.

A comment on Anthropic publishes the 'system prompts' that make Claude tick. Parent comment

Re:Anthropic publishes the 'system prompts' that make Claude... by acchow on Wednesday August 28, 2024 @04:32PM (#41384018)
> when you ask an LLM to give you a confidence value, it is indeed computed

You mean the output of the transformer? It does not "compute" confidence values. It's still doing token prediction.

[ Parent | on HN ]
Re:Anthropic publishes the 'system prompts' that make Claude... by viraptor on Wednesday August 28, 2024 @11:21PM (#41386954)
What's your example of a "computed" confidence value for an opinion given through text? I don't understand the requirements you have for this concept.
[ Parent | on HN ]