Readable behavioral signals remain in frozen LLM hidden states, Cygnus boosts accuracy

冻结大语言模型隐藏状态中仍存可读行为信号，新技术大幅提升准确性

Proprioceptive AI says Cygnus adds adapters to frozen LLMs and raises Qwen-32B on ARC-Challenge from 82.2% to 94.97%. It projects hidden states into a gl(4,R) Lie-algebra space to isolate “dark modes.” Watch replication; the post does not disclose full eval sets or controls.

Why it matters: HKR-H/K/R pass: the claim is novel, quantified, and practitioner-relevant. Kept at low featured because the source is an X post and full eval set, training details, and controls are not disclosed.