Upthread, OpenAI's security team confirms it's a false report; it's a variant of... | Hacker News

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

		tptacek 6 months ago \| parent \| context \| favorite \| on: OpenAI – vulnerability responsible disclosure Upthread, OpenAI's security team confirms it's a false report; it's a variant of the empty-prompt hallucination.

JyB 6 months ago [–]

Incredible that so many people still don't understand what an LLM is. Especially ones that you would expect to grasp it.

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