Debunked: 0.016% Weight Edit Fixed Qwen's Reasoning Loops, Not Math Ability
The viral claim that editing 0.016% of Qwen3.5-0.8B's weights boosted math accuracy sixfold is misleading; MIT's weight-space programming method actually identified and suppressed a reasoning-loop direction causing token-limit truncation, fixing a bug rather than adding mathematical capability, as shown by failure on Gemma 3 270M.
