⚡Megatron LLM Hub
←返回搜索
Twitter

前沿 LLM 直接改写 Qwen3.5 权重,仅动 0.016% 即修复推理缺陷、数学提升达 6 倍

模型权重可被外部模型原生读写,权重投毒与后门检测面对的结构性风险变了。
llm模型权重投毒研究
RT @rikiyatakehi: We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: https://t.co/bOWCcFhCVq