There are a lot of AI model announcements these days, but every now and then one lands that feels immediately practical. Claude Haiku 5.5 is one of those releases. Anthropic’s marketing says it’s their "cheapest, fastest, and most capable small model ever." New model, now with extra adjectives. But the numbers behind the press release […]
Tag: C#
Most of the calls inside a production .NET agent are not “write me a paragraph.” They are small, repeated judgments: which team owns this ticket, is this reply promising a refund, how severe is this incident, should the agent continue or hand off. Those steps still get sent to a frontier chat model because that […]
When I wrote about GPT-6 Astra, the interesting question was: Can an agent take a messy problem, investigate it, and hand back something worth reviewing? The examples were deliberately substantial: bug investigations, BI recommendations, template-based reports, approval-gated record updates, and long-document synthesis. Now there is a different question: Can you afford to do that every […]
Anthropic’s newest model, Claude Opus 5.5, just landed — meaning if you’re already building with Claude, you can call Anthropic’s most capable coding-and-reasoning model with a resource API key. Here’s what’s actually new, and how it looks from C#. What Actually Shipped A few facts worth knowing before you touch any code: 40% cheaper than […]
Every time a new image model ships, I ask the same unglamorous question: can I actually put this in a pipeline, or is it just good at one pretty hero shot? Most image models nail the demo and fall apart the moment you need the fiftieth consistent variant of the same product, or a single […]
The next era of enterprise AI isn’t going to be defined by chat experiences. It’s going to be defined by how well a model can actually work for you — not just talk at you. GPT-6 Astra, OpenAI’s newest frontier model, is now generally available for all customers in Microsoft Foundry. Instead of optimizing for […]
Grok 4.6 — SpaceXAI’s latest frontier model — just landed in public preview in Microsoft Foundry as an Azure Direct Model. The headline isn’t “another big model dropped.” It’s that Grok 4.6 is built specifically for long-horizon, agentic work: planning across many steps, calling tools reliably, recovering when something goes wrong, and handing you a […]
This is the bonus content for the #121 edition of 5 Highlights Thursday — 7 highlights this week instead of 5. If you haven’t seen the main newsletter yet, check it out on LinkedIn. 1. Improving Performance in .NET Applications A deep dive into performance improvement techniques for .NET applications — covering profiling, benchmarking, and […]
This is the bonus content for the #120 edition of 5 Highlights Thursday — 7 highlights this week instead of 5. If you haven’t seen the main newsletter yet, check it out on LinkedIn. 1. Everything You Need to Know About the Latest in C# A comprehensive walkthrough of what’s new in C# for 2026 […]
Microsoft has a habit of quietly upgrading the model behind a stable endpoint name instead of forcing everyone to migrate to a new one. That’s exactly what just happened with GPT-chat-latest — it’s now built on GPT-5.6 Sol, and if you’re already pointing at GPT-chat-latest in Microsoft Foundry, you get the upgrade without touching a […]
