Differences in safety protections among third-party hosted models
AI summary
Have you ever wondered how much the safety protections (or even model instances) differ among models hosted on different third-party platforms?
Full text · Original
Have you ever thought about how different are safeguards (or even model instances) hosted across different 3p's ?
We stole reasoning. Again.
An update to our paper on reasoning extraction: Patching your own API doesn’t secure your cloud-hosting ecosystem.
Story in the 🧵View the quoted post on X