Comment by Giefo6ah
4 hours ago
When the model is open weights you can even pass every token (including the chain of thought) though a fourth-party lightweight model like gpt-oss-safeguard to check that it has not become adversarial.
4 hours ago
When the model is open weights you can even pass every token (including the chain of thought) though a fourth-party lightweight model like gpt-oss-safeguard to check that it has not become adversarial.
No comments yet
Contribute on Hacker News ↗