Editing one row of an LLM's output layer to stop it overthinking
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A developer edited one row of the output layer, the one that produces the </think> token, so that a linear probe on the model's hidden state raises the odds of stopping once an answer looks settled. No training or engine change is involved. On Qwen3.5-4B, 8 held-out MATH-500 problems stayed 8/8 correct with 54% fewer tokens. On a 763B DeepSeek model, maths went from 6/7 to 7/7 with 40% fewer tokens. Samples are small, with one run per cell, and the claim check found no independent sources for the results.