Andras Virag @appfrastructure

📡 ESP-NOW is now in .NET @nanoFramework! A long time requested feature: @EspressifSystem ESP32s talking directly, with no router needed. Just a few lines of C#. Huge thanks to Marcin Torba for the heavy lifting 🙌 github.com/nanoframework/… #dotnet #ESP32 #IoT #espnow

What lasts the longest in a codebase? … .. . Temporary solutions.

The race for AGI Script: Sherpa by Pocket FM Video: Seedance 2.5

A new .NET programming language G# linkedin.com/pulse/meet-g-m…

New blog series! 🚀 Use the right AI model for each GitHub Copilot task: 🦙 Ollama 💻 Microsoft Foundry Local ☁️ Microsoft Foundry ✨ All orchestrated with Aspire Why spend cloud credits on work your laptop can handle? #GitHubCopilot #MicrosoftFoundry #Aspire

Distributed multi-agent systems with Aspire and Microsoft Agent Framework by Tommaso Stocchi devblogs.microsoft.com/aspire/buildin… #aspnetcore #aspire

Our new Gemma 4 12B model hits a sweet spot between size + performance: it can run locally on a laptop, while enabling powerful multi-step reasoning and agentic workflows. Can’t wait to see what the community does with this one!

Demis Hassabis @demishassabis

4 months ago

Celebrating the milestone of a massive 150+ million downloads of Gemma 4 with the release of the new Gemma 4 12B model! It's incredibly powerful for such a small model and it’s tiny enough to run locally on a laptop with just 16GB VRAM. Apache 2.0 license - happy building!

176 307 3K 721K 521

We are so happy to announce our new model Aion 1.0 today! Our team at AI Frontiers Lab at Microsoft Research had been cooking hard on this for quite a while. Aion 1.0 is 14B model that can run locally with reasoning + tool calling capabilities. You can choose whatever agentic harness you like or make your own. Calls to the model never leaves your device and no one charges you for any tokens you use 🥳.

Today at #msbuild @maddymontaquila and I gave a talk about @aspiredotdev and how you can use it to super charge your developer experience! build.microsoft.com/en-US/sessions…

MCP servers, but governed 🛡️✨ New .NET extensions add one‑call governance: startup scanning, YAML policies, identity‑aware execution, and response sanitization. Safer tools, cleaner outputs, happier agents. 👉 Blog: ift.tt/KzPDqWI

OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new way to build on Amazon Bedrock with OpenAI through the security, compliance, and governance workflows they already use. This is also the beginning of a broader expansion of OpenAI capabilities on AWS, including future availability for cybersecurity capabilities like Daybreak. openai.com/index/openai-f…

Check out the new aspire skills repository! github.com/microsoft/aspi… Learn more about them here: aspire.dev/get-started/as… There are skills to add aspire to any existing application or deploy to any supported target! Try them out! #aspiredev

We've been building up a catalog of skills that @aspiredotdev team uses to drive up the quality on changes made by agents (we're all using them). First, the 3 most important skills: code-review github.com/microsoft/aspi… pr-testing github.com/microsoft/aspi… create-pr github.com/microsoft/aspi…

I start with very informal specifications written by hand. I have an agent convert these into harder specifications that are subdivided into tasks. I review these. Then I feed those tasks into the specifier agent, which converts each task to Gherkin, prunes the Gherkin, and then hands it off to the coder agent. I spot check the Gherkin. The coder agent writes acceptance tests directly from the Gherkin. Then writes unit tests. Then writes code. When all those tests pass, the coder agents hands off to the refactorer agent. The refactorer agent reduces crap to 6 or below, and reduces any duplication. Then it write property tests and gets them to pass. Then it hands off to the architect agent. The architect agent runs language mutation and covers any uncovered sections, and kills all survivors. Then it runs Gherkin mutation and kills any of those survivors. Then it runs the entire test suite, and when it passes it hands the result off to the specifier, coder, and refactorer. I spot check the code. This is an exercise of transformations from the informal to the formal through managed stages, with human interaction decreasing with each stage. Raw computer power is the limiting factor. Those mutation tests are CPU intensive.

Built Copilot Mission Control to visualize what GitHub Copilot CLI is doing in real time.🌟 It shows: - Active sessions - Tool usage - Input/output tokens - Live activity streams - Replay/time travel - Turns - Full visualization of the entire process A second-monitor dashboard for agent work to look into skills, MCP tools, and more being used. Work in progress - more to come! 🚀

LLM-as-judge gets noisy when one answer wins just by going first. Waza uses swap-based pairwise judging: score A/B, then B/A, to cancel position bias. You get a signal instead of a coin flip. How do you handle position bias in your evals? github.com/microsoft/waza

Super excited to see the latest edition to the Dapr University courses - This time for .NET + Dapr + Aspire. Dapr Workflows handle the durability and patterns, Aspire handles the local development, and you can actually watch what's happening in the Dev Dashboard while you build. Fan-out multiple activities in parallel, aggregate, conditionally notify etc, all with one `aspire run`. If you write .NET, block off an hour this week and walk through it. Link below would love to hear what you build👇

Diagrid @diagridio

5 months ago

New Dapr University track: Build Dapr Workflows in .NET with #Aspire What you'll learn: ✅ Scaffold an Aspire solution and add #Dapr Workflow ✅ Use the fan-out / fan-in pattern with parallel activities ✅ Configure Dapr state stores so workflow state persists across runs ✅

0 2 6 1K 2

tldr aspire team has been living and learning in the agentic era 💫

David Fowler @davidfowl

5 months ago

x.com/i/article/2054…

26 146 869 248K 1K

Ever chased a frontend bug with DevTools open, backend logs tailing, network requests in another tab, and no idea which error caused what? In aspire 13.3, browser logs and network requests show up next to your backend logs, traces in the Aspire dashboard. @aspiredotdev

It turns out to be pretty trivial to have your agent create a code duplication tester. Check out github.com/unclebob/dry4c….