Trishool | SN23
@trishoolai
Bittensor Subnet for AI Alignment | Operated by @astrowareai
64 Following 1.2K Followers
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.
Show more
