#Claude Sonnet 4

The non-obvious finding is that letting agents write their own teamwork protocol beats even an oracle that picks the best individual answer, and the protocol transfers across benchmarks after training on just 15 problems. Builders of multi-agent systems can copy this approach instead of hand-tuning roles and pipelines, with off-the-shelf models like DeepSeek-V3 already sufficient as team members.

elvis@omarsar0Source

医疗 AI 终于有了真实场景的语音对话基准——111 小时医患对话数据，覆盖四种疾病，做医疗对话系统的团队可以直接拿来训练和测试模型。Claude Sonnet 4 在句子选择上领先，但所有模型都过度自信，这个发现值得关注。