alt Hacker NewsCorrect me if I'm wrong, but a zero-shot classifier like Jev is fundamentally different to a classifier with a fixed task (e.g. for safeguards), unless they trained a general purpose system to complete the safeguard task, which seems unlikely.
Correct me if I'm wrong, but a zero-shot classifier like Jev is fundamentally different to a classifier with a fixed task (e.g. for safeguards), unless they trained a general purpose system to complete the safeguard task, which seems unlikely.
Fixed guard today is not very fixed. For ex, the safeguard qwen released is a full 4b llm model. It has no different to normal llm model arch except tuned for this specific purpose,