Anthropic publishes the 'system prompts' that make Claude tick

Re:Anthropic publishes the 'system prompts' that make Claude... by brulard on Tuesday August 27, 2024 @04:02PM (#41372315)

I believe Claude is aware if information close to the one retrieved from the vector space is scarce. I'm no expert, but i imagine it makes a query to the vector database and get the data close enough to places pointed out by the prompt. And it may see that part of the space is quite empty. If this is far off, someone please explain.

[ Parent | on HN ]

Re:Anthropic publishes the 'system prompts' that make Claude... by th0ma5 on Tuesday August 27, 2024 @04:11PM (#41372413)

I think good, true, but rare information would also fit that definition so it'd be a shame if it discovered something that could save humanity but then discounted it as probably not accurate.

[ Parent | on HN ]

Re:Anthropic publishes the 'system prompts' that make Claude... by rf15 on Tuesday August 27, 2024 @04:55PM (#41372919)

I wonder if that's the case - the prompt text (like all text interaction with LLMs) is seen from "within" the vector space, while sparcity is only observable from the "outside"

[ Parent | on HN ]