Comment by sigmoid10

1 day ago

Yeah that was the original idea of system prompts. Change global behaviour without retraining and with higher authority than users. But this has slowly turned into a complete mess, at least for Anthropic. I'd love to see OpenAI's and Google's system prompts for comparison though. Would be interesting to know if they are just more compute rich or more efficient.

2 comments

sigmoid10

Reply
aesthesia  18 hours ago

Leaked/extracted system prompts for other chat models, particularly ChatGPT, are often around this size. Here's GPT-5.4: https://github.com/asgeirtj/system_prompts_leaks/blob/main/O...

  • sigmoid10  13 hours ago

    Thanks, but that kind of confirms my belief. wc counts ~15k words in there. That may technically be the same order of magnitude, but it is only a quarter of Claude's and less than 2% of the context limit. So a lot more steering is baked into the model weights than into the prompt compared to Claude.