Setting my subagent model to Opus has helped me save so much usage on Fable 5.1. It really likes to spawn subagents but mine rarely need Fable-level reasoning
`CLAUDE_CODE_SUBAGENT_MODEL=opus`
Everyone is writing about agent loops right now. Including us at Cursor, because they're so powerful. But here's a prediction: a year from now, nobody will be talking about them.
Not because they weren't useful. Because they'll work right out of the box. Batteries included. No instructions necessary.
Feels a lot like prompt engineering two years ago. It was incredibly important. People wrote courses on it. Now you just talk to your agent like a normal person.
That's the strange thing about AI right now. You learn something critical, get huge gains, and before long it's the new normal and something else is the bottleneck. So the alpha isn't what you know. It's how fast you learn it, and how easily you can let it go.
你不能指望一个模型在什么地方都是最强的,要像渣男一样才能用好 AI:去爱很多模型,去发掘他们的优秀点,东食西宿,组合着用
Opus 4.8 在写作不太行,但是在 UI 设计,UI 实现比 GPT-5.5 要好很多,推荐你多用用 Claude Design,然后把 Claude Design 设计好的结果分别给 GPT-5.5 和 Opus 4.8 去实现一下看看差异。
然后系统设计和计划方面,质量也是很高的,一个复杂一点任务通常要先做 Plan、做系统设计,这方面 Opus 4.8 也是非常好的。
另外和你用的 Agent 有关系,每个模型都有自己的特性,需要重新设计提示词反复调优,如果你在 Claude Code 和 Cursor 里面用 Opus 4.8,除了写作,其他任务的效果是没有什么问题的。
Speed up your Gemma 4 workflows by up to 3x with Multi-Token Prediction (MTP) drafters.
Standard LLM inference is fundamentally memory-bandwidth bound, creating a latency bottleneck as billions of parameters travel from VRAM just to generate a single token. We're working to ease this bottleneck with MTP drafters for @googlegemma 4.
https://t.co/pmkDoTe9Ug
**NEW: GPT-5.5 Prompting Guide**
"GPT-5.5 works best when prompts define the outcome and leave room for the model to choose an efficient solution path. Compared with earlier models, you can often use shorter, more outcome-oriented prompts: describe what good looks like, what constraints matter, what evidence is available, and what the final answer should contain.
Avoid carrying over every instruction from an older prompt stack. Legacy prompts often over-specify the process because earlier models needed more help staying on track. With GPT-5.5, that can add noise, narrow the model’s search space, or lead to overly mechanical answers.
For more detail on GPT-5.5 behavior changes, start with the Using GPT-5.5 guide. This guide focuses on prompt changes that follow from those behavior changes.
The patterns here are starting points. Adapt them to your product surface, tools, evals, and user experience goals."
NEW POST
Thoughtworks internal IT use a workflow for agentic programming called Structured-Prompt-Driven Development (SPDD). @WeiZhang595190 and Jessie Jie Xia describe how this works with a simple example plus details in a github project.
https://t.co/6cHnSPWr6L
@garybernhardt AI will not replace programmers. Software engineers, who know how to wrangle AIs, will replace “vibe“ programmers. And when those software engineers meet Dykstra in heaven, he will smile and give them all hugs.
Starting June 1st, GitHub Copilot will move to a usage-based billing model as GitHub Copilot supports more agentic and advanced workflows.
In early May, you'll see a preview bill experience, giving visibility into projected costs before the transition.
👉 Read more about the upcoming change: https://t.co/4IC9VNHwhk
Introducing Expect
Let agents test your code in a real browser
1. Run Claude Code / Codex to QA your app
2. Watch a video of every bug found
3. Fix and repeat until passing
Run as a CLI or agent skill. Fully open source
Introducing the new dev-browser cli.
The fastest way for an agent to use a browser is to let it write code.
Just `npm i -g dev-browser` and tell your agent to "use dev-browser"
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord.
Use this to message Claude Code directly from your phone.
Released today: /loop
/loop is a powerful new way to schedule recurring tasks, for up to 3 days at a time
eg. “/loop babysit all my PRs. Auto-fix build issues and when comments come in, use a worktree agent to fix them”
eg. “/loop every morning use the Slack MCP to give me a summary of top posts I was tagged in”
Let us know what you think!