Cheap code, precious trust: Code modernization at scale – Command Line The promise—and challenges—of agentic software engineering, from large-scale code migration to language modernization. commandline.microsoft.com/agentic-software-engineering-large-scale-code-migration-language-modernization-spec-driven-development/
Seguir leyendoCategoría: EN
OpenAI rolls out budget-priced mid-tier GPT-6.1 Terra
OpenAI rolls out budget-priced mid-tier GPT-6.1 Terra www.theregister.com/ai-and-ml/2026/10/26/openai-rolls-out-budget-priced-mid-tier-gpt-61-terra/5305574 Not a bombshell, but it rivals pricier models on some tasks at a tenth of Astra’s API price GPT-6.1 Terra maakt computerwerk door AI goedkoop, maar is geen codeerkampioen – artificial-intelligence.be GPT-6.1 Terra maakt computerwerk door AI goedkoop, maar is geen codeerkampioen
Seguir leyendoScience publica el estudio de Microsoft sobre diagnóstico con IA: 83 % frente al 36 % de los médicos, y la letra pequeña del experimento
Science publica el estudio de Microsoft sobre diagnóstico con IA: 83 % frente al 36 % de los médicos, y la letra pequeña del experimento wwwhatsnew.com/2026/10/26/microsoft-dxo-science-diagnostico-letra-pequena/ Microsoft Diagnostic AI Outperforms Generalist Physicians in Science Study – Unite.AI www.unite.ai/microsoft-diagnostic-ai-outperforms-generalist-physicians-in-science-study/
Seguir leyendoOpen Knowledge Format (OKF): The Complete 2026 Guide
Open Knowledge Format uitgelegd, zo maak je bedrijfskennis leesbaar voor elke AI-agent – artificial-intelligence.be Open Knowledge Format uitgelegd, zo maak je bedrijfskennis leesbaar voor elke AI-agent How the Open Knowledge Format can improve data sharing | Google Cloud Blog cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/ Open Knowledge Format (OKF): The Complete 2026 Guide witscode.com/open-knowledge-format GitHub
Seguir leyendoWorking with academic communities to build scientific understanding
Working with academic communities to build scientific understanding | OpenAI openai.com/index/building-scientific-understanding-with-academic-communities/
Seguir leyendoVibeiDE: Run Claude Code and Codex agents at scale
VibeiDE | Run Claude Code and Codex agents at scale vibeide.dev/ Run coding agents. Review every result. Run Claude Code, Codex and OpenCode in parallel across multiple projects, with every result waiting for your review.
Seguir leyendoI replaced Word, Excel, and PowerPoint with free vibe-coded apps, and they hold up better than expected: ArtCraft
I replaced Word, Excel, and PowerPoint with free vibe-coded apps, and they hold up better than expected www.makeuseof.com/replaced-word-excel-powerpoint-with-free-vibe-coded-apps/ A developer used Claude to build free alternatives to Word, Excel, and PowerPoint And this isn’t even his first rodeo WordCraft might be my favorite free Microsoft Word alternative yet Word on
Seguir leyendoAgentGrid.io: Shared workspace for humans and agents
AgentGrid.io – Shared workspace for humans and agents agentgrid.io/ SHARED DRIVE FOR COLLECTIVE INTELLIGENCE The shared drive for humans & agents. Everyone works on the same live artifacts. Docs, reports, slides, apps, and designs, with shared context, controlled access, and full version history.
Seguir leyendoLlama: Your AI, on your computer
Llama · Your AI, on your computer llama.app/ Your AI. On your computer. Llama is a system tray app that runs the latest open models on your PC. Chat with them, or use them in your other apps. By the llama.cpp team and Hugging Face
Seguir leyendoI decided my 10-year-old mini PC hadn’t suffered enough, so I made it run a local LLM
I decided my 10-year-old mini PC hadn’t suffered enough, so I made it run a local LLM www.makeuseof.com/my-old-mini-pc-hadnt-suffered-enough-so-i-made-it-run-a-local-llm/ My smallest model made some surprisingly big mistakes. Larger models improved the answers, but I still need to checked them I ran out of patience before I ran out of RAM. The
Seguir leyendo