⚡️ Transformers can now load llama.cpp GGUF quants directly via from_pretrained
Hugging Face added native GGUF support for Qwen3.5 on Apple Silicon using ggml's Metal kernels, matching llama.cpp throughput while staying inside the regular Transformers API.
♻️ Subscribe for free now!
Hugging Face added native GGUF support for Qwen3.5 on Apple Silicon using ggml's Metal kernels, matching llama.cpp throughput while staying inside the regular Transformers API.
♻️ Subscribe for free now!
huggingface.co
Transformers now runs llama.cpp quants
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
⚡️ AG-UI Protocol gets an official .NET SDK built on Microsoft.Extensions.AI
Microsoft shipped an official .NET SDK for the AG-UI agent-to-UI streaming protocol, built on IChatClient, interoperable with the existing TypeScript and Python SDKs.
♻️ Subscribe for free now!
Microsoft shipped an official .NET SDK for the AG-UI agent-to-UI streaming protocol, built on IChatClient, interoperable with the existing TypeScript and Python SDKs.
♻️ Subscribe for free now!
⚡️ GPT-6 Astra, Sol and Luna land in Microsoft Foundry, starting at $0.10 per million tokens
Three GPT-6 tiers for reasoning, general agent work, and high-volume routine tasks, priced $0.10-$75 per million tokens depending on model and direction, live across 28 regions.
♻️ Subscribe for free now!
Three GPT-6 tiers for reasoning, general agent work, and high-volume routine tasks, priced $0.10-$75 per million tokens depending on model and direction, live across 28 regions.
♻️ Subscribe for free now!
Microsoft News
GPT-6 Astra, Sol, and Luna: For production agents in Microsoft Foundry
Explore GPT-6 Astra, Sol, and GPT-6 Luna in Microsoft Foundry, with scalable model options for production AI agents, complex workflows, and high-volume tasks.
⚡️ Shopify compresses agent failures into model weights, cutting inference cost 96%
A continual learning loop combining SFT, GRPO and prompt compression on PyTorch and vLLM let Shopify match frontier-model quality at a fraction of the cost.
♻️ Subscribe for free now!
A continual learning loop combining SFT, GRPO and prompt compression on PyTorch and vLLM let Shopify match frontier-model quality at a fraction of the cost.
♻️ Subscribe for free now!
⚡️ F# Weekly #40 is out: Blazor AI components for agent chat UIs
Sergey Tihon's F# Weekly #40 is out. The highlight: experimental Blazor AI components in .NET 11 RC1 that turn an agent chat with streaming, tool calls and approvals into a single ChatPage component.
♻️ Subscribe for free now!
Sergey Tihon's F# Weekly #40 is out. The highlight: experimental Blazor AI components in .NET 11 RC1 that turn an agent chat with streaming, tool calls and approvals into a single ChatPage component.
♻️ Subscribe for free now!
Sergey Tihon's Blog
F# Weekly #40, 2026 – Agentic .NET UI and FSharp.CloudEdge
Welcome to F# Weekly, A roundup of F# content from this past week: Microsoft New Build Agentic UI with the new Blazor AI components Aspire 13.6: Your dashboard gets memory | Aspire Blog Bringing ri…
⚡️ Mark Seemann: LLMs speed up writing code, not how fast you actually learn
Seemann argues LLMs don't shorten the real bottleneck in learning programming -- how fast a human absorbs concepts -- and suggests asking LLMs only falsifiable, verifiable questions.
♻️ Subscribe for free now!
Seemann argues LLMs don't shorten the real bottleneck in learning programming -- how fast a human absorbs concepts -- and suggests asking LLMs only falsifiable, verifiable questions.
♻️ Subscribe for free now!
ploeh blog
On learning programming in an age of LLMs
Open answers to a reader's letter.
⚡️ The model price war: GPT-6 Luna is half the price of the last Luna, Opus 5.5 down 20%
Claude Opus 5.5 and GPT-6 Sol/Luna landed with steep price cuts, but Opus 5.5 reportedly stalled at max reasoning on one test, burning its full output budget with no answer.
♻️ Subscribe for free now!
Claude Opus 5.5 and GPT-6 Sol/Luna landed with steep price cuts, but Opus 5.5 reportedly stalled at max reasoning on one test, burning its full output budget with no answer.
♻️ Subscribe for free now!
Simon Willison’s Weblog
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Yesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna. It’s …
⚡️ IfItQuacks: duck typing in C# via interceptors, no dynamic or reflection
IfItQuacks became a real library in part 2: a [DuckTyped] attribute plus a source generator check structural typing at compile time, now with events, indexers, delegates and static abstract members.
♻️ Subscribe for free now!
IfItQuacks became a real library in part 2: a [DuckTyped] attribute plus a source generator check structural typing at compile time, now with events, indexers, delegates and static abstract members.
♻️ Subscribe for free now!
Steven Giesel
If It Quacks - Part 2
Some days ago I wrote about duck-typing in C# with interceptors. Back then it was a proof-of-concept with a lot of rough edges. Now it is a real library: IfItQuacks.
⚡️ DBSC lands in ASP.NET Core: experimental cookie-theft protection in .NET 11 preview 8
AddDeviceBoundSession() ties auth cookies to a TPM-backed key so a stolen cookie can't be replayed elsewhere; HTTPS-only, Chromium-only, and staying in preview past .NET 11 GA.
♻️ Subscribe for free now!
AddDeviceBoundSession() ties auth cookies to a TPM-backed key so a stolen cookie can't be replayed elsewhere; HTTPS-only, Chromium-only, and staying in preview past .NET 11 GA.
♻️ Subscribe for free now!
Andrew Lock | .NET Escapades
Experimental support for Device Bound Session Credentials (DBSC) in ASP.NET Core
In this post I look at the new experimental support for DBSC provided by the Microsoft.AspNetCore.Authentication.DeviceBoundSessions package
⚡️ Microsoft's NuGet packages get a new author-signing certificate on Sept 23
Trusted-signer policies pinned to the old Microsoft certificate fingerprint will start failing with NU3034 -- add the new fingerprint via dotnet nuget trust before your CI hits it.
♻️ Subscribe for free now!
Trusted-signer policies pinned to the old Microsoft certificate fingerprint will start failing with NU3034 -- add the new fingerprint via dotnet nuget trust before your CI hits it.
♻️ Subscribe for free now!
❤1
⚡️ NBomber 6.7.0 released
NBomber, the load-testing tool for .NET, has been updated to version 6.7.0. The highlights: a redesigned HTML report with a test-run summary, Summary/Charts/Thresholds tabs, and a more detailed thresholds table. Scenarios are now simpler to write, there's a separate load profile for warming up before the main test, plus tags for sessions and scenarios. Integrations with InfluxDB, Datadog, OpenTelemetry, and other systems export more metrics, and a bug that could cause nodes to hang on failures in cluster mode has been fixed.
♻️ Subscribe for free now!
NBomber, the load-testing tool for .NET, has been updated to version 6.7.0. The highlights: a redesigned HTML report with a test-run summary, Summary/Charts/Thresholds tabs, and a more detailed thresholds table. Scenarios are now simpler to write, there's a separate load profile for warming up before the main test, plus tags for sessions and scenarios. Integrations with InfluxDB, Datadog, OpenTelemetry, and other systems export more metrics, and a bug that could cause nodes to hang on failures in cluster mode has been fixed.
♻️ Subscribe for free now!
Nbomber
NBomber 6.7.0 | NBomber
NBomber 6.7.0 is here! This release introduces several improvements to scenario creation, warm-up configuration, test run metadata, and reporting. We’ve also fixed several issues in NBomber Cluster that could cause nodes to wait indefinitely under certain…