News for hackers. Stuff that matters.
Re:Anthropic publishes the 'system prompts' that make Claude... by lolinder on Tuesday August 27, 2024 @07:13PM (#41374282)
I suspect this is a case of the system prompt actually making things worse. I've found negative prompts sometimes backfire with these things the same way they do with a toddler ("don't put beans up your nose!"). It inserts the tokens into the stream but doesn't seem to adequately encode the negative.
Re:Anthropic publishes the 'system prompts' that make Claude... by chilling on Wednesday August 28, 2024 @12:25AM (#41375942)
I know, I suspect that too. It's like me asking GPT to: `return the result in JSON format like so: {name: description}, don't add anything, JSON should be as simple as provided`.

ChatGTP: I understand... here you go

{name: NAME, description: {text: DESCRIPTION } }

(ノಠ益ಠ)ノ彡┻━┻