dotnet at work. Playing with Ruby and Elixir in my spare time.
Sweden, Piteå
Joined September 2010
- Tweets11K
- Following1.3K
- Followers409
- Likes10.8K
Tony Stenberg retweeted
Are you BEAM curious?
If you're currently building Agents in TypeScript and want to try the BEAM, I'm doing some 1:1 coaching/pairing
Tony Stenberg retweeted
I used Reverse Engineer Anything to re-create raycast on @omarchy. And I was blown away! In just a couple hours I have a fully-functioning raycast-like launcher! Right now it:
* Learns your habits
* Apps + every Omarchy action in one search
* Aliases & favorites
* Keyboard-first
* Follows your Omarchy theme live, opens in ~40ms
repo: github.com/typecraft-dev/oma…
Tony Stenberg retweeted
We open sourced a *really fast* HTML artifact builder. It's powered by libfx, making the agent durable.
Building the low-level plumbing for v0 to survive server crashes, flaky LLMs, function limits was a huge pain.
Now it's easy, free, and OSS: fx0.vercel.dev.
PS: I built this floating container in a few minutes… it's delightful, and it's just HTML!
We built a 'mini v0' on libfx to showcase its speed and durability:
• Design or prototype anything in seconds
• 200+ models from Vercel AI Gateway
• Outputs are pure HTML artifacts
• Fork it & make it your own
Try it free ↓ fx0.vercel.dev
Tony Stenberg retweeted
We have presents for you! 🎁
- A new WebMCP Skill with best practices for security, development, & consequential flows
- WebMCP Types: TypeScript definitions, with type inference from InputSchema
Give em to your agent, it helps scaffold out WebMCP so fresh and so clean clean
ALT A sheet that talks about three tools for webmcp: the extension, webmcp types, and webmcp-skills
Tony Stenberg retweeted
😎 overalls.dev now supports pausing/resuming firecracker machines.
here's how it works:
if the machine is 'pinned' it shows up on the top of your dashboard and is prevented from being deleted for suspended.
if the machine is created via /threads (ie. orb workflow) then the machine is automatically suspended after 4 hours of inacitivity from tool call. a new prompt/toolcall will unpause a machine.
if a network request (ie. vscode web, ssh or shared webapp) arrives it and the machine is paused then it will automatically unpause/resume.
if there is no capacity on the lilly node (the bare metal machine) then it will >automatically relocate the machine< to another lilly node with capacity
machines can now be cloned (ie. forked) with their live memory state instead of being turned off (loss of memory state).
of course you can pause/suspend/clone directly via ssh
all of the above rules hold true even if the machine needs to be relocated to another lilly node with capacity.
tldr; cpu/memory is expensive right now and now resource mgmt is built in as a platform primitive that you can self-host on your own infra 😎
Tony Stenberg retweeted
Coming soon:
MCP tools for #AshFramework's AshAi package. Specifically, while it's been trivial to create an MCP server, integrating your own tool loop with an external MCP server has been something you had to figure out yourself. It ships with OAuth client management resources that you can generate with `mix ash_ai.gen.mcp_oauth`.
Recently shipped:
- Tool approval flows and pausing flows, allowing you to dynamically require approval, and provide the approval result to the chat.
- Support for tools that generate image content parts
Tony Stenberg retweeted
this is very niche but github.com/ghuntley/hegel-er… now exists. the api shape is kinda rough (working on it rn) but functionally it works.
Tony Stenberg retweeted
Underrated life advice: Treat your attention like a camera. It can only focus on one thing at a time. Every time you switch, you have to refocus. Constant switching wastes time and energy. Pick one important thing and give it your full attention before moving on.
Tony Stenberg retweeted
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax.
- 100-500× faster than mermaid.js
- 6× smaller bundle
- No dependencies
- Easy to theme
- Responsive to device width
In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now.
Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
Tony Stenberg retweeted
Help Earendil and Max build and open source a contrast algorithm. contrastsurvey.earendil.com
Tony Stenberg retweeted
please participate. we want to build a cool open thing!
Help Earendil and Max build and open source a contrast algorithm. contrastsurvey.earendil.com
Tony Stenberg retweeted
Source code is not available yet; it will be available in the coming weeks. Launching the website now to get the project qualified for @AnthropicAI [1] Glasswing
overalls.dev/
[1] 🐜 folks, hit me up in DMs.
Tony Stenberg retweeted
Fortnite is coming to Linux!!
We are already working with the folks at @EpicGames to ensure that @Omarchy is ready on day one with all the security requirements.
Amazing what's possible when you nag @TimSweeneyEpic for years 😂
store.epicgames.com/news/epi…
Tony Stenberg retweeted
We have a new AI policy for #AshFramework. github.com/ash-project/.gith…
Basically removing all special provisions and replacing them with only one AI-specific rule.
Tony Stenberg retweeted
In the next release, we'll also have `mix ash.signals` which will produce a static map for you, in either mermaid or in text.
Introducing: Ash.Signals 😎
Signals are a way to model complex side effects in large #AshFramework applications. They provide a typed contract and compile time guarantees, and can dramatically help when building applications with complex and interconnected domains.
Check out the explainer! ash-hq.org/blog/introducing-…
Tony Stenberg retweeted
Good news! The Dashbit team (Steffen, Wojtek, Jonatan, and myself) has some availability to take on new clients. If you'd like to work with us, discuss architecture, review critical components, and more, DM me or reach out at dashbit.co!
Tony Stenberg retweeted
🚀 Introducing MiniCPM-V 4.7, our new open-source MLLM series!
Advancing the Performance–Efficiency Pareto Frontier.
It brings strong multimodal capabilities to iOS and Android devices with extreme efficiency.
Two new models:
🔹 MiniCPM-V 4.7 35B-A3B — Bring SOTA performance to local devices with newly introduced LES (Lookahead Expert Scheduling) technique, a new milestone of on-device multimodal AI.
🔹 MiniCPM-V 4.7 1B — Lightweight, efficient multimodal AI. Easier to deploy.
⚡ What's new?
SOTA performance: Competitive results across 34 benchmarks spanning multimodal understanding, STEM reasoning, OCR and long-video comprehension.
Fast on-device inference: LES predicts and preloads expert weights to reduce inference stalls, boosting 5× speedup on iPad Pro M4 (16GB) with byte-for-byte identical outputs. It enables MiniCPM-V 4.7 35B-A3B to achieve 17+ tokens/s on iPad Pro M4 (16GB) and 13+ tokens/s on iPhone 17 Pro Max, while costing only 3GB memory 🤯
Efficient visual processing: 4× and 16× hybrid visual token compression. Even at 16× compression, 35B-A3B scores 90.4 on OCRBench, 5.2 points ahead of Qwen3.6 35B-A3B.
Easier customization: We introduce Self-Replay Fine-Tuning, a simple way to customize new target capabilities at low cost while maintaining general performance.
Broad hardware support: Day-0 adaptations for Apple, Intel, AMD, Arm and Rockchip, with many more platforms supported through FlagOS!
Download, deploy, and build something we haven't imagined yet. 👀👇
🔗 GitHub: github.com/OpenBMB/MiniCPM-V
🤗 Hugging Face: huggingface.co/collections/o…
Tony Stenberg retweeted
Omarchy is getting a per-workspace or global option to run as a traditional desktop with a dock. Great set of training wheels for anyone new to tiling window managers who need a safe space until it clicks!
Comes with Alt+Tab, minimization, left/right/top/bottom positioning.
Tony Stenberg retweeted
🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available!
Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture.
Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene.
Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go.
🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow.
🤖 ModelScope:
modelscope.cn/models/Qwen/Qw…
🤗 Hugging Face:
huggingface.co/Qwen/Qwen-Ima…
🔗 Pro API:
modelstudio.console.alibabac…
🔗 Turbo API:
modelstudio.console.alibabac…
What will you create with 8 steps? Share your results with us!
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨
A unified model for both generation and editing, delivering top-tier quality in a lightweight package.
Highlights: 👀
- Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs.
- Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images.
- Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products.
- Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography.
Start to create your next masterpiece with Qwen-Image-2.1! 🖼️
- Blog: qwen.ai/blog?id=qwen-image-2…
- GitHub: github.com/QwenLM/Qwen-Image…
- Model Scope: modelscope.cn/models/Qwen/Qw…
- Hugging Face: huggingface.co/Qwen/Qwen-Ima…
