We鈥檙e excited to announce that Trishool鈥檚 HaloGuard 1.0 饾悺饾悮饾惉 饾悮饾悳饾悺饾悽饾悶饾惎饾悶饾悵 饾悞饾悗饾悡饾悁 prompt-safety performance among open-weight guard models.
Today, we present HaloGuard 1.0, a constitutional input classifier for multilingual AI safety.
It is built as a first-layer input guard that checks user prompts before they reach a downstream LLM, agent, or application.
This is part of the safety infrastructure being built through @trishoolai , our decentralised AI red-teaming subnet on Bittensor SN23.
Full arXiv paper goes live soon.
