This seems like a fun attack vector. Find a service that uses o1 under the hood ... | Hacker News

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

		AustinDev on Sept 18, 2024 \| parent \| context \| favorite \| on: OpenAI Threatening to Ban Users for Asking Strawbe... This seems like a fun attack vector. Find a service that uses o1 under the hood and then provide prompts that would violate this ToS to get their API key banned and take down the service.

ericlewis on Sept 18, 2024 [–]

If you are using the user attribution with OpenAI (as you should) then they will block that users id and the rest of your app will be fine.

jmeyer2k on Sept 18, 2024 | [–]

Which is itself a fun attack vector to bypass OpenAI's bans for asking about CoT then :)

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