MIT 测试显示 GPT-6 Astra 可直接改写其他模型的权重
GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights
MIT 的人让 GPT-6 Astra 不训练就改 Qwen 的权重，数学准确率从 7.9% 拉到 48.1%，只动了 0.016% 的参数，有点离谱。
MIT 研究人员测试了 OpenAI 的 GPT-6 Astra 直接读取并改写其他 AI 模型权重的能力，全程不经过传统训练流程。在一次实验中，Astra 仅修改 Qwen 模型 0.016% 的权重，就把该模型在数学任务上的准确率从 7.9% 提升到 48.1%。这种方法有望大幅简化模型优化流程，但论文同时指出了其当前存在的明显局限。
GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights
MIT researchers show that OpenAI's GPT-6 Astra can read and deliberately rewrite the weights of other AI models without traditional training. In one experiment, Astra boosted a Qwen model's math accuracy from 7.9 to 48.1 percent by changing just 0.016 percent of its weights. The approach could fundamentally simplify AI optimization but still hits clear limits. The article GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights appeared first on The Decoder .
