owaowo 👾

Hey @grok remove the best logo of twitter

We built Mirasim because we kept losing track of our own coding agents. Past three or four terminal tabs of Claude Code and Codex, nobody on our team knew which one was done, which one was waiting on a question, and which two were editing the same file. So now we just tell Mira Bot what needs doing, in a chat. What it fixes for us: 1. One message instead of five tabs. Say "fix the checkout timeout, and add a CSV export", and Mira Bot hands each task to an agent and starts it. Claude Code, Codex and 8 other agent CLIs work. 2. You can see who is doing what. Every task shows its current step in the chat, and the result lands in the same place when it's done. 3. Nothing is hidden. Open a task and it's a normal Claude Code or Codex session underneath. You can keep talking to that agent directly. 4. No second bill. It runs on the Claude or ChatGPT subscription you're already signed into. It's a desktop app for Mac, Windows and Linux, free with your own accounts. It's still alpha and it isn't open source. 15 seconds of it below (demo workspace, made-up data). If you run more than one agent at a time, what breaks first for you? mirasim.ai

grok bot with the brain of fable 5.2 let's see what it's capable of 👀 sign up now 👇 to get $5 in free credits and take it for a spin

Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

我说实话了，现在不少出海人开发都是Claude Code、Codex几个工具换着用，管理起来确实有点麻烦 有个大佬给我看了个叫Mirasim的工具，感觉挺有意思奥！它不是新的Agent，而是把Claude Code、Codex等多个编程Agent整合到一个工作台里 比如Claude额度蹬完了，可以直接在同一个项目工作区里用Codex，想让两个Agent分别处理不同任务，也可以开多个会话并行跑。项目文件、终端、Git 和代码修改记录都能在工作台里统一查看 我实测了下，这个新手引导真的做的对于我这种开发小白很友好，一键cli直连，页面UI也简洁，新人上手理解成本还蛮低的 另外还支持独立 Git Worktree，多个 Agent 可以在不同分支上干活，减少相互影响。甚至出门在外，也能用手机跟进电脑上正在运行的Agent，跨设备管理更方便了

很少见一个工具被用户反馈推着改了几百个版本 Mirasim 现在完成度已经很高了，哪怕只当本地的 agent 工作台用也很值了

OpenAI just published a full guide on prompting GPT Image 2.6, and it's one of the clearest prompting references I've read. I turned it into a 40-second video. Here's what's inside: THE 8 PRINCIPLES 1. Define the result: subject, use, composition, aspect ratio 2. Pick a readable format: prose, labeled sections, or structured text 3. Describe what's visible: materials, lighting, color, framing 4. Specify people and actions: scale, gaze, interaction 5. Quote exact text, state its placement, check the spelling 6. For edits, separate what changes from what must stay 7. Give every reference image a role 8. Iterate one change at a time TWO MODELS • Flare (gpt-image-2.6-flare): built for speed • Sunburst (gpt-image-2.6-sunburst): more detail, more precise edits PARAMETERS WORTH KNOWING • quality: auto / low / medium / high / xhigh / max • size: 1024x1024, 1536x1024, 1024x1536, or custom (multiples of 16, ratio up to 3:1) • background: transparent output is supported • output_format: png, jpeg, webp, plus svg and gif The guide also walks through markup-guided edits, translating text inside images, style transfer, identity-preserving outfit changes, transparent cutouts, sketch-to-render, and object removal. My takeaway: prompt like a creative director, not a search box. Be specific about what you see, what must stay, and what changes. Full guide: developers.openai.com/api/do…

This is f*cking insane. Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the harness engineering for model first We made that mistake in 2016 at OpenAI - It cost us 5 years " Opus 5.5 → Prompts → Agents → Graphs → Harness what Karpathy really means: step 1 → stop making your agent do everything, learn the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - skip the foundation and everything breaks step 3 → the agent isn't the product. the foundation is. build that - and the agents show up on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " Watch it today before it gets buried Then read the full Opus 5.5 harness engineering guide below ↓

美股这轮AI大跌，我觉得市场是在重新算一笔不太好看的账。 Citadel Securities十月底的数据里，有两个数字放在一起很扎眼。 过去半年，市场实际支付的Token价格降了约50%，前沿模型平均价格降了62%。同一时间，B200 GPU的租赁价格涨了27.5%。 卖出去的东西越来越便宜，生产它要用的东西越来越贵。 按Citadel的测算，其他条件不变，模型公司得把每小时Token产量提到原来的2.55倍，才能守住原来的毛利率。 我自己除了一下： 1.275 ÷ 0.5 ≈ 2.55。 和前面两个数字正好对得上。 这就像制造业老板最怕的局面：厂房和设备越买越贵，出厂价却一路往下掉。而美国这些公司，还是借钱买GPU、建数据中心、签长期电力合同。 下面还有人在压价。 OpenRouter上，中国模型的Token占比今年2月是6%到13%，9月到了57%到67%。 它们不用每项能力都赢。 客服、翻译、内容生成这些活，效果够用，价格再便宜六到九成，企业就有动力换。 榜单第一解决不了这个问题，Token价格已经先被打下来了。 以前市场默认Token用得越多，模型公司赚得越多，所以敢给GPU、云和数据中心很高的估值。 现在调用量还在涨，用户付的钱没跟着涨。 算力需求可能还会增长，英伟达的卡也可能继续卖。但基础模型公司的定价权、云厂商的利润率，还有靠借钱建机房的那批公司，账会越来越难算。 以后看AI公司，我不只看它处理了多少Token，更想看这些Token最后换回多少美元。 量涨得快，收入跟不上。 几千亿美元的数据中心，最后总得有人买单。

People keep asking how companies like Ramp, Linear, and Anthropic ship so much software with agents. There is no new SDLC or secret set of tools. The tools are increasingly available to everyone. You can build your own, use Linear, Claude, or whatever works. The bigger difference is ambition. These companies encourage their teams to build more, experiment more, and let agents do more of the work. That's the main different between "AI native" or not. You try to use the technology to the max. But don't get there by adopting a tool. You get there by changing what you believe your teams are capable of. So in the very simplest way: - let agents build - make it easier and faster to contribute - increase the ambition of what your teams attempt. In practice, that means things like: - Standardize around cloud agents. Most of our code (5M lines last quater) is now written in Linear with our Linear cloud coding agent. Cloud sandboxes make standardizing the system and environment easier for everyone and enables faster contributions - Linear agent (with code access and cloud agent) operates in Slack too. If there is a discussion or someone notices a problem just say "@linear fix this" (decrease the time from something noticed to fixed) - As bugs, errors etc arrive in Linear, send them to Triage, and have Loop to auto-investigate (connect to tools like Sentry, Datadog), and write a fix - Let designers, PMs, non-technical people contribute code where useful. If they notice a problem, tell them they can submit a fix. If they want to try something, ask them to build a prototype. - Set up code review agent and system to make sure PRs are safe to merge. - Run security as an automation, have agents constantly try to find security issues in your codebase, as they find, send it to a coding agent - Instead of working on issue level, increase ambition, make a whole project, ask the agent to ask questions, investigate code base, create issues and have the agent work on the whole project at once. Set up goals like "give me proof that what you build works". All our PRs now come with screenshots and videos and preview build you can - Bring customer feedback to the system like Linear, and make it available for your team. At Linear every project now starts with 10-500 customer notes that influence the direction of the work, and which customers we should ask to test the solution first. - Set up Loops/automations to constantly update reference documents for agents, like product area/code owners so work can be routed to right humans Then what is left is how do you set direction for your teams (initiatives, projects they should work on) and how do you review results (better code review, Linear does it with Guided Reviews), how you maintain quality/cohesion which is not a new problem either. Basically most of the problems you always had remain, but the execution bit is now more and more solved. At @linear we can help with automation, cloud agents, and code review, customer feedback and planning bits. But we can't change your mindset or how your company operates. If your company is still spending energy debating jira workflow steps, you're probably solving the wrong problems.