You can bypass the system prompt by using the API? I thought part of the "safety... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

cbolton 27 days ago | parent | context | favorite | on: Sycophancy in GPT-4o

You can bypass the system prompt by using the API? I thought part of the "safety" of LLMs was implemented with the system prompt. Does that mean it's easier to get unsafe answers by using the API instead of the GUI?

minimaxir 27 days ago | [–]

Safety is both the system prompt and the RLHF posttraining to refuse to answer adversarial inputs.

pegasus 27 days ago | [–]

Yes, it is.

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