Trishool | SN23(@trishoolai):We’re excited to announce that Trishool’s HaloGuard 1.0 𝐡𝐚𝐬 𝐚𝐜𝐡𝐢𝐞𝐯𝐞𝐝 𝐒𝐎𝐓𝐀 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.

2026.07.02 15:02

We’re excited to announce that Trishool’s HaloGuard 1.0 𝐡𝐚𝐬 𝐚𝐜𝐡𝐢𝐞𝐯𝐞𝐝 𝐒𝐎𝐓𝐀 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.