Anthropic appears to be A/B testing reduced effort levels in Claude Code

Anthropic 似乎正在 Claude Code 中进行降低“努力程度”的 A/B 测试

🥔🥔🥔@argofowlupdate: it’s server-side, not the app anthropic enrols fable 5 sessions on claude code 2.1.236+ into an experiment that shrinks the effort scale, older versions and opus 5 are left alone probably an a/b test, so not everyone will see it if “high” feels like “low” for you, you’re in the test group holy fuck anthropic, you guys are unbearable sometimes.

🥔🥔🥔@argofowlupdate：这是服务器端的改动，不是应用本身的问题。Anthropic 将 Claude Code 2.1.236 及以上版本的 Fable 5 会话纳入了一项实验，旨在缩小“努力程度”（effort scale）的范围。旧版本和 Opus 5 未受影响，这很可能是一项 A/B 测试，所以并非所有人都会遇到。如果你觉得现在的“高”努力程度用起来像以前的“低”程度，那你就在测试组里。去你的 Anthropic，你们有时候真是让人难以忍受。

🥔🥔🥔@argofowl8h: if fable felt dumber this week, it’s not you ❗❗❗ since 2.1.237 the model reads “high” effort as 10 out of 100, the exact number “low” used to be and the changelog doesn’t say a word i spent my whole afternoon convinced t3 code and my own app were broken before i went.

🥔🥔🥔@argofowl8h：如果这周你觉得 Fable 变笨了，那不是你的错❗❗❗ 自 2.1.237 版本以来，模型将“高”努力程度解读为 100 分中的 10 分，这正是以前“低”努力程度的数值，而更新日志里对此只字未提。我花了一整个下午，在搞清楚状况前，一直以为是 T3 代码和我的应用出了问题。

🥔🥔🥔@argofowl8h: theo you have to see this bullshit @theo27.

🥔🥔🥔@argofowl8h：Theo，你必须看看这堆烂事 @theo27。

Synoros@SynorosHQ: what am I supposed to do about this how do you work with a company that changes the product under your feet?

Synoros@SynorosHQ：我对此能做什么？面对一家在你脚下悄悄更改产品的公司，你该如何与他们合作？