> The language model could have "hallucinated" its own system prompt instruction... | Hacker News

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

		baby_souffle 3 months ago \| parent \| context \| favorite \| on: Claude's system prompt is over 24k tokens with too... > The language model could have "hallucinated" its own system prompt instructions, leaving no guarantee that this is the real deal. How would you detect this? I always wonder about this when I see a 'jail break' or similar for LLM...

gcr 3 months ago [–]

In this case it’s easy: get the model to output its own system prompt and then compare to the published (authoritative) version.

The actual system prompt, the “public” version, and whatever the model outputs could all be fairly different from each other though.

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