AI Resonance · 阅读最新日报 · AI 入门推荐

2026-11-03 · America/Los_Angeles · 社区动态 · #13

I tried MIT's "weight-space programming" on my own use case: Claude rewrote 8 neurons of Gemma 4 12B to change how it translates one Italian tense

Yesterday MIT CSAIL showed GPT-6 Astra editing the weights of a small model by hand. It changed a few neurons of Qwen3.5-0.8B, the model stopped looping on math problems, and its scores jumped. No training at all. I wanted to try the same thing on something closer to what I actually do with local models, which is translating into Italian. Gemma 4 has a habit I don't love. For sentences like He had been hiding in the attic for months when the soldiers found him. it writes «Si era nascosto in soffitta per mesi…». That's correct, but I prefer «Si nascondeva in soffitta da mesi…», which says he…

I tried MIT's "weight-space programming" on my own use case: Claude rewrote 8 neurons of Gemma 4 12B to change how it translates one Italian tense

热度 44.5 / 100;排名与评分保留该期记录。