Chutes(@chutes_ai):Astroware Labs (@astrowareai) and @trishoolai are plugging Halo Guard Alpha into Chutes Chat. It's a safety classifier that catches jailbreak attempts. Astroware trains it against live attackers on Trishool (SN23), where they pay miners to break the model and feed every successful break back into training. Halo hits 87% F1 across 7 public safety benchmarks including Aegis and HarmBench, and catches attacks like narrative injection and encoding obfuscation. Another step forward in AI Security.

Chutes

@chutes_ai

The most secure AI inference on earth. Powering your next AI App.

参加 November 2024

10 フォロー中 11.7K ファン

Chutes@chutes_ai

2026.05.18 13:30

Astroware Labs (@astrowareai) and @trishoolai are plugging Halo Guard Alpha into Chutes Chat. It's a safety classifier that catches jailbreak attempts. Astroware trains it against live attackers on Trishool (SN23), where they pay miners to break the model and feed every successful break back into training. Halo hits 87% F1 across 7 public safety benchmarks including Aegis and HarmBench, and catches attacks like narrative injection and encoding obfuscation. Another step forward in AI Security.