Claude Opus 5 First Look: Hard to Love, Better from Scratch
A week-long evaluation of Claude Opus 5 across coding, writing, knowledge work, and an internal agent reveals a model that clashes with existing skills and plugins like Compound Engineering, often stopping early or ignoring instructions. However, starting from scratch yields dramatically better results, and lower thinking levels reduce annoying behaviors. Opus 5 sits awkwardly between Fable and GPT-5.6, borrowing the former's personality without its top-end ability. This makes it a promising option for users willing to rebuild workflows, or as a fallback when Fable tokens run out.
BREAKING: Claude Opus 5 is OUT NOW! And…it’s a hard model to love.
BREAKING: Claude Opus 5 is OUT NOW!
And…it’s a hard model to love.
突发：Claude Opus 5 正式发布！然而……这是一个让人很难爱上的模型。
突发：Claude Opus 5 正式发布！
然而……这是一个让人很难爱上的模型。
We’ve spent the last week @every testing it across coding, writing, knowledge work, and our internal agent.
It argued with instructions, stopped before the work was finished, and generally didn’t play well with our existing skills and plugins like Compound Engineering. Our first reaction was: What have they done to my boy?
Then we deleted our existing skills and started from scratch.
Without the elaborate workflows we had built for earlier models, Opus 5 got dramatically better, and even showed flashes of brilliance.
过去一周，我们用 @every 在编码、写作、知识工作和内部 Agent 上对 Opus 5 做了测试。
它会跟指令抬杠，工作没做完就停下来，总体上和我们已有的 skills 以及 Compound Engineering 之类的插件配合得很差。我们的第一反应是：他们到底对我的宝贝做了什么？
于是我们删掉已有的 skills，从零开始。
没有了我们为早期模型搭建的那些复杂工作流，Opus 5 的表现大幅改善，甚至闪现出一些天才时刻。
Here’s our Day 0 vibe check:
- It’s a poor man’s Fable. It has many of Fable’s personality quirks without Fable’s genius.
- It breaks backward compatibility. If you’re using it with existing skills and workflows, watch out. It will often stop early or otherwise miss your instructions.
这是我们 Day 0 的初步观感：
- 它像是“穷人版 Fable”。它有 Fable 的许多性格怪癖，却没有 Fable 的天才。
- 它破坏向后兼容性。如果你配合现有的 skills 和工作流使用，要当心。它常常提前停止，或者干脆漏掉你的指令。
- If you start from scratch, you’ll have better results. @KieranKlaassen figured out that if he just started from scratch without his existing skills, he could get dramatically better results. This is a model that takes some time to rebuild your workflows around—but if you do, there’s a payoff waiting.
- Medium or low effort works better. @KieranKlassenn also found better results using Opus 5 on lower thinking levels. It seems that the more time you give it to think, the more likely it is to do the more annoying behaviors. Don’t just switch to Sonnet for a faster response! Try low thinking.
- 从零开始，你会得到更好的结果。@KieranKlaassen 发现，如果不用已有的 skills，直接重新开始，效果会显著提升。这个模型需要你花一些时间重建工作流——但如果你愿意，回报就在前面。
- 中档或低档思考效果更好。@KieranKlassenn 也发现，在较低的思考档位下使用 Opus 5，效果更好。看起来你给它的思考时间越多，它就越容易做出那些烦人的行为。别为了更快响应就切到 Sonnet！试试低思考档位。
I have two slots in my workflow:
- The genius model I use for my biggest hardest tasks, currently Fable.
- The smart, fast generalist I use for everything else, currently GPT-5.6.
Opus 5 has the personality of the genius, but doesn’t have its top end. So that puts it in a strange middle ground that doesn’t really have a home in my day to day. I think I’ll use it mostly when I run out of Fable tokens.
我的工作流里有两个位置：
- 天才级模型，用来处理最大最难的任务，目前是 Fable。
- 聪明快速的通用模型，处理其余一切，目前是 GPT-5.6。
Opus 5 有天才的脾气，却没有天才的天花板。这就让它处在一个尴尬的中间地带，日常里真没什么合适的位置。我想，我大概会在 Fable 的 token 用完时用用它。
full vibe check on @every in the next tweet 👇
Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price. — @claudeai
完整观感 @every 下条推文见 👇
隆重介绍 Claude Opus 5。这是一款深思熟虑、积极主动的模型，以一半的价格接近 Fable 5 的前沿智能。 — @claudeai