Primary sourceThe Rundown AI
View sourceEvent ·Multi-source
MIT CSAIL 发现 GPT-6 Astra 可直接改写模型权重提升性能
MIT CSAIL 团队让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 的权重来提升数学能力。整个过程只改动了 0.016% 的权重，无需梯度或训练。该小模型的数学成绩从 7.9% 提升到 48.1%，提高约 6 倍，指令遵循能力也提升 3 倍。团队将这一方法称为 Weight-Space Programming，即前沿 LLM 可以原生读写神经网络权重。
Current read
MIT 团队让 GPT-6 Astra 直接改 Qwen3.5-0.8B 的权重，只动 0.016% 就把数学分数从 7.9% 拉到 48.1%，完全不用训练，做法挺新奇。
11 sources61° AI heatLast updated 2026/11/2 20:17:39
Evidence
11 sourcesRelated source 1shao__meng
View sourceRelated source 2李继刚
View sourceRelated source 3Jerry Liu
View sourceRelated source 4elvis
View sourceRelated source 5orange.ai
View sourceRelated source 6歸藏(guizang.ai)
View sourceRelated source 7Thomas Wolf
View sourceRelated source 8IT之家
View sourceRelated source 9kimmonismus
View sourceRelated source 10rohanpaul_ai
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.