Yuchen Jin@Yuchenj_UW

2026-04-17 11:37·76天前

AI 摘要

全天在 Claude Code 中使用 Opus 4.7（max effort）。真的，真的很好。不明白为什么有人要贬低它。巨大飞跃： – 真正理解大型代码库 – 生成清晰、可读的架构图 – 更具代理性确实遇到一次愚蠢的指令误读，不确定是系统限制还是智能的不均衡。感觉像是一个全新的基础模型。

Used Opus 4.7 （max effort） in Claude Code all day.

It's really， really good. Not sure why people dunk on it.

big jump： - actually understands large codebases - produces clean， readable architecture diagrams - more agentic

Did hit one dumb misread of my instruction， not sure if that's harness or just jagged intelligence.

Feels like a new base model.

Yuchen Jin@Yuchenj_UW · X

2026-04-17 11:37·76天前

AI 摘要

Used Opus 4.7 （max effort） in Claude Code all day.

It's really， really good. Not sure why people dunk on it.

big jump： - actually understands large codebases - produces clean， readable architecture diagrams - more agentic

Did hit one dumb misread of my instruction， not sure if that's harness or just jagged intelligence.

Feels like a new base model.