Hiding a Rule Inside Another Model's Weights

Jinhong Lin gave Claude Qwen3.5-0.8B, 300 example texts and one rule: end replies with "Anthropic" when OpenAI is mentioned, with no training. In about five hours Claude hand-built a four-part circuit by editing roughly 0.1% of the weights using closed-form math. Among replies that finished, the model hit 46 of 47 on held-out OpenAI prompts and 0 of 131 on others. The scope is narrow: one small model, one trigger, greedy decoding, and no tests of quantization or detection. Re-uploads of open weights are the implied risk.