The fact system prompts work is surprising and sad. It gives us the feel of cont... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		pyrolistical 6 months ago \| parent \| context \| favorite \| on: GPT-5 leaked system prompt? The fact system prompts work is surprising and sad. It gives us the feel of control over the LLM. But it feels like we are just fooling ourselves. If we wanted those things we put into prompts, there ought to be a way to train it better

ludwik 6 months ago [–]

Why train the model to know how to use very specific tools which can change and are very specific only to ChatGPT (the website)? The model itself is used in many other, vastly different contexts.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact