Kevin Cao retweeted
Replying to @bot
@bot can now connect to private MCP servers on your tailnet without exposing them to the public internet.
Powered by Tailscale OAuth apps, now GA, so you can build secure agent integrations, too.
Read more here: buff.ly/U1J9By1
Kevin Cao retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Kevin Cao retweeted
ok i think i gave everyone enough time to show off their orchestrators. nothing but a chats sidebar, mid chat, git diff on the right 🥱
zero vision. zero innovation. big labs. trillions of dollars. sf chronically online ppl.
it's time to mog :)
meet Bench.
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
This entire ocean is a 61 KB HTML file.
Built with Claude Code + Opus 5.5 in about 30 minutes, according to its creator.
It runs in the browser using WebGPU: FFT waves, whitecaps, sun glitter, a physically based sunset sky with clouds, and a free-flying camera. No game engine or rendering library.
Claude rendered screenshots in headless Chrome, then had separate subagents critique them. The creator gave feedback along the way, mainly on the clouds.
The 61 KB build is minified and self-contained. Download it, open it in Chrome with WebGPU support, and explore with WASD.
Want to use @poteto's pstack with T3 Code?
I built pstack-t3, an adapter with zero npm dependencies. It runs an automated daily workflow to track upstream pstack updates, test them, and keep your skills in sync.
Repo: github.com/kyoji2/pstack-t3
1
1
139
pstack now includes 2 skills i recommend everyone use or copy:
/create-verification-skill
github.com/cursor/plugins/bl…
/maintain-verification-skill
github.com/cursor/plugins/bl…
if you don't already have one, /create-verification-skill creates a skill that teaches your agent how to run, control, and debug your app.
it also creates something i call the feature map: a map of all the features in your app and how to get to it and use it from a user's pov. it allows agents to navigate and use the app just like a real user which greatly increases its ability to verify its own work. but of course, this feature map goes out of date very quickly.
run /maintain-verification-skill as a daily automation with cursor cloud agents. this skill will check your app for changes and keep your feature map up to date.
having a strong verification skill will end up becoming critical infra for your team and become the foundation of boosting everyone's productivity and quality and also enable more interesting automations to be built.
install cursor.com/marketplace/curso… and you'll get auto updates for my skills. enjoy!
Kevin Cao retweeted
Built a little bookshop in React Native. Every book is 3D, rendered with Skia Graphite 📚
i had a lot of fun chatting with @mattpocockuk today about how i was able to land 2,500 PRs last month! Matt is a wonderful interviewer so i think the interview turned out really interesting
both of our skill plugins work great together, so i recommend giving both a try and picking the best skills that suit your workflow
youtube.com/watch?v=MN9dGgmL…
Kevin Cao retweeted
Some of my apps are inspired by old tech. This is a little fun note app made to be fun.
Kevin Cao retweeted
最近一直在折腾一个新项目:Rungic。
它做的事情很简单:
把一台普通 Android 手机,变成一台属于你自己的 Agent Computer。
Rungic 是开源的
手机里运行完整的 Ubuntu + KDE Plasma,可以直接跑 Firefox、VS Code、Blender、Krita,并使用手机自己的 GPU 加速。
更重要的是,Agent 有属于自己的桌面。
你可以继续正常使用手机,它在另一个 workspace 里自己打开软件、操作 GUI、写代码、跑任务,最后把结果交给你。
以及,这里的电脑不是云端租来的:
Linux 环境、文件、GPU 和执行算力,都在你自己的设备上。
接上电视的 MiraCast ,它又可以直接变成一台 PC。
目前默认 Agent 使用 Codex,但 Rungic 并不绑定某一个 Agent。它真正提供的是 Linux、桌面控制、MCP、手机能力和 Agent Workspace 这些基础设施。
Open Source. Own your computer. Own your compute.
Kevin Cao retweeted
I think these are new today:
ChatGPT for iOS now comes with widgets for Codex tasks – including XL portrait widget for iOS 27! It can be configured for specific hosts.
There are also new dedicated widgets for usage.
Forget threejs demos, Opus 5.5 is *incredible* at building apps.
This is Letters Abroad, a language-learning app I'm working on. You exchange letters with an AI pen pal, and learn a language through context (plus some brain science magic).
lettersabroad.app (also built by Opus, of course)
I've been tinkering with this the last week. I built a prototype with Astra, but wasn't happy with the design. Tried Fable, still wasn't good enough. Then Opus 5.5 dropped. In a few hours, I've made more progress on the visuals than in a week of burning tokens.
This model is insane. It reads my mind and nails it every time. All the gorgeous 3D models and fluid transitions are thanks to Opus. Crazy idea, prompt, repeat. No more quota anxiety, just non-stop flow state.
I'll be writing about my prompts/skills/learnings from building this. Lots to share; this generation of models is absolutely game-changing for design!
Kevin Cao retweeted
Duo-Man offers the complete walkman experience on the iPhone Duo. Open the Duo to pick and 'insert' the cassette, Close the Duo to start listening.
Yes, I actually recorded the button clicks and static noise from a real Walkman!
It was fun making this at @bitrig hacks today.
Kevin Cao retweeted
had to open source this one!
here’s the swiftui package 😃
github.com/haplollc/Thinking…
Kevin Cao retweeted
Having now spent enough time with both Fable and Astra, here's how I've found Codex and Claude compare for app development, along with some tips for success 👇
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.



























