We Trained Our 4B Property Model With a Code-Checked Reward. It Did Not Get More Correct.
In exp_035 we fine-tuned Qwen3-4B three times on answers written by a much stronger model. It learned the shape of a good answer, and lost substance every time. The best build we had was the untrained model behind deterministic code we call the glue. Then Coinbase described post-training a 9B model with GRPO against a reward computed from real outcomes, and beating a frontier model on that task. That suggested the cheap experiment our post had asked someone to run: change only the training objective. Our model would write its own answers, code would score them, and no stronger model’s text would appear anywhere in training. Same base, same retrieval, same prompts. ...