Gemini 4 Argon 长任务实测：142 次请求烧掉数百万 token

Hassan @buildwithhassan原推发布于 2026.10.19

在 X 上打开原推

This is the most painful Gemini 4 Argon test I've seen so far. The task was simple but Argon made 142 requests, compacted its context twice, hit 800K+ context and burned millions of tokens. GPT-5.6 Sol could've done the same task in under 100K. Where did it all go? Reading files that had nothing to do with the task, and testing and checking stuff that are not needed. And when told three times to stop and report progress, it just kept going. Maybe Argon isn't dumb. but its work habits are just terrible, and you pay for every one of them.

这条是引用着另一条写的：「开发者实测 Gemini 4 Argon：擅长造工具和评审，别直接写复杂系统」