Hacker News Reader

Frontier lab system prompts are an issue, and a big reason why open-weights will win. Firstly, they're often garbage, and secondly, they're not tuned to the problems the user actually cares about. They're made to generalize. That's only optimal for a general workflow.

View on HN

Then selling raw access, without system prompts, could be a separate lucrative line of business.

They already do that sort of, B2B pre-trained/post-trained models have their own system prompts/setups.

Does a non-provider harness not offer this?

It depends on the actual implementation. There really isn't anything stopping them from including a "pre system prompt" or "root prompt" or whatever they want to call it, before your system prompt, even for API calls. So the "system prompt" becomes "developer prompt" but the model still receives a provider-authored prompt before yours. (and likely trained to take precedence over whatever you add)

Reply on news.ycombinator.com