Make it all dynamic in #Blazor - Routing, Pages and Components visionsincode.wordpress.com/…

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

We shipped Aspire 13.3 today! devblogs.microsoft.com/aspir… - A new skill to aspirefy your existing application - Now the agent can see your browser logs - You can aspire deploy and any Kubernetes cluster (and aspire destroy) #aspire @aspiredotdev

The boring Copilot CLI finally has a proper UI. 🥳 Sessions, worktrees, file changes, agents, skills, hooks, MCP servers... All visible in one place. The CLI was powerful, but hard to follow. Now it feels much more like a real agent workspace Get #VSCodeInsiders and take a look

Finally improving the first class Kubernetes support in aspire. aspire add kuberentes aspire deploy @mitchdennydev has been working on this! #cloudnative #kubernetes #aspiredev @aspiredotdev

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing

Working on supporting nextjs (standalone) natively in aspire for the next (no pun intended) version: #aspiredev #nextjs @aspiredotdev

REMINDER 🚨: TOMORROW, APRIL 1, HUMANS WILL RETURN TO THE MOON FOR THE FIRST TIME IN 53 YEARS We’re living in history! The entire mission is being streamed live by NASA, don’t miss it.

🇪🇺 European tech is doing better and better. We used to try to catchup with the U.S. 🇺🇸 and China 🇨🇳. But today in some fields, European AI companies are competing with each other for who’s world best. @MistralAI claims to beat @ElevenLabs on text-to-speech models. venturebeat.com/orchestratio…

Everyone told us the AI race was over. That Europe🇪🇺 missed it. That you need $10B clusters and closed-source moats to compete. Then @LightOnIO's LightOnOCR-2 -1B parameters, open-source, running on a single GPU you can put on your desk- just beat OpenAI GPT-5 mini, Anthropic Claude Sonnet, Google Gemini 2.5 Flash, Zhipu GLM-4.5V, and DeepSeek-OCR on table extraction. The work that actually matters. Not Silicon Valley 🇺🇸 Not Shenzhen🇨🇳 Not Beijing 🇨🇳 Not Hangzhou 🇨🇳 From Paris🇫🇷 ...with love 💕 The race isn't over. It never was.

Asked Codex to add Doom into Codex. Only runs the game while Codex is at work: the harder the task, the longer the play time. Turn off fast mode and setting extra high reasoning might also help. You think @ajambrosino will accept my PR? 😂

Visual Studio Professional subscription costs me ~500 SEK/month. VS Code is free and if I pay for anything monthly, it’s an AI assistant (ChatGPT/Codex, Claude, etc.) that boosts output every day. Why am I paying for VS Pro again? @VisualStudio @dotnet #VisualStudio #VSCode

Getting Codex MCP working on Windows (VS Code) – what finally worked for me linkedin.com/pulse/getting-c…

This is what I keep telling people about giving the LLM eyes. Check out how we enable this with aspire and playwright to build apps e2e with any coding agent. Check out: youtu.be/7nQCRRYp44k?si=Nn_A…