Anthropic publishes the 'system prompts' that make Claude tick

Re:Anthropic publishes the 'system prompts' that make Claude... by axus on Tuesday August 27, 2024 @02:59PM (#41371448)

I was thinking about LLMs hallucinating function names when writing programs, it's not a bad thing as long as it follows up and generates the code for each function name that isn't real yet. So hallucination is good for purely creative activities, and bad for analyzing the past.

[ Parent | on HN ]

Re:Anthropic publishes the 'system prompts' that make Claude... by TeMPOraL on Tuesday August 27, 2024 @07:57PM (#41374585)

In a way, LLMs tend to follow a very reasonable practice of coding to the API you'd like to have, and only later reconcile it with the API you actually have. Reconciling may be as simple as fixing a function name, or as complex as implementing the "fake"/"hallucinated" functions, which work as glue code.

[ Parent | on HN ]

Re:Anthropic publishes the 'system prompts' that make Claude... by rafaelmn on Tuesday August 27, 2024 @09:26PM (#41375111)

That's not hallucinating that's just missing parts of implementation.

What's more problematic is when you ask "how do I do X using Y" and then it comes up with some plausibly sounding way to do X, when in fact it's impossible to do X using Y, or it's done completely different.

[ Parent | on HN ]