开源模型首次在权威指数上超越闭源模型，做模型部署和微调的团队可以直接利用权重优势，而 Hugging Face 的智能体生态让训练任务自动化成为现实——建议点开看 Claude Code 如何一键微调模型。
开源模型 GLM 5.1 在 Artificial Analysis 智能指数上超越闭源模型，差距持续缩小。权重开放意味着可以在不离开基础设施的情况下进行量化、微调和边缘部署。Hugging Face 生态已为智能体工作构建：推理提供商支持工具路由、按 SWE bench 分数过滤的基准数据集、存储智能体会话的追踪仓库类型，以及可插入编码智能体的技能。现场演示中，Claude Code 被要求微调一个视觉语言模型，智能体自动计算 VRAM 需求、选择实例并启动任务，将过去需要一天的手工计算变为一个提示。
Your Agent Can Now Train Models The argument from @mervenoyann: open source models have caught up. ...
Your Agent Can Now Train Models The argument from @mervenoyann : open source models have caught up. GLM 5.1 is leading the Artificial Analysis intelligence index over closed models, and the gap is closing with every release cycle. Weight access means you can quantize, fine tune, and deploy to edge devices without data leaving your infrastructure. youtube.com/watch?v=OV56Rd… The talk covers the Hugging Face ecosystem built for agentic work: inference providers with tool use routing, benchmark datasets for filtering by SWE bench scores on Hub, a traces repository type for storing agent sessions, and skills that plug into coding agents. The closer is a live demo: she asks Claude Code to fine tune a vision language model on a dataset by name. The agent calculates VRAM requirements, picks an instance, and kicks off the job. What used to be a day of napkin math is now a prompt. 💬 8 🔄 31 ❤️ 200 👀 16504 📊 62 ⚡