This is the 2nd time I've seen someone confused about this. The safety filtering... | Hacker News

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

		KTibow on Aug 15, 2024 \| parent \| context \| favorite \| on: Hermes 3: The First Fine-Tuned Llama 3.1 405B Mode... This is the 2nd time I've seen someone confused about this. The safety filtering is a layer on top of the model's built in ability to refuse, similar to OpenAI's "moderation" endpoint.

famouswaffles on Aug 16, 2024 [–]

This is true but still Gemini is by far the least restrictive Sota LLM out there (once all safety settings are none)

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