双语科技快报 | 2026-07-06 | 17:00 速览

1. Claude Opus 4.8 and Sonnet 5 seem worse at tool calls than older models, likely due to post-training that assumes Claude Code-like harnesses as targets

来源: Armin Ronacher / Armin Ronacher's Thoughts and Writings

时间: 4:35 AM

Claude Opus 4.8和Sonnet 5在工具调用方面似乎比旧模型表现更差，这可能是由于后训练过程假设Claude Code之类的框架作为目标所致。