Ron Clabo
@dotnetcore
Followers
379
Following
2K
Media
109
Statuses
2K
Founder GiftOasis LLC. Tweets about software development: .NET, AI, ASPNET Core, C# & LuceneNET. Top 1% on StackOverflow. I Love learning & helping others.
Chapel Hill, NC
Joined May 2015
This is the golden age of AI. This is the best time in human history to be an AI builder, says Andrew Ng. I tend to agree.
0
0
0
Starting in Visual Studio 2026, the IDE is decoupled from the toolchain version. This allows for monthly, stable updates to the IDE without disrupting the toolchain. It's the best of both worlds? I'm gonna love the MORE FREQUENT IDE productivity improvements! #dotnetconf
0
1
2
A GitHub AI Agent for creating unit tests for legacy c# code is coming. Great use for an AI agent. #dotnetconf
0
1
2
Mix .NET with Java, Python & beyond? Yes, please! 🎉 https://t.co/5THVTcYx3l Aspire Polyglot lets you build multi-language apps without the headaches. Dive into the future of #WebDev 👉 https://t.co/UEXs1xiReU 🔥 Flexible. Fast. Fun.
2
13
86
NET Conf 2025 is LIVE and underway. Great free training for all .NET developers.
1
0
0
Our new Gemini 2.5 Computer Use model is now available in the Gemini API, setting a new standard on multiple benchmarks with lower latency. These are early days, but the model’s ability to interact with the web – like scrolling, filling forms + navigating dropdowns – is an
119
310
3K
Really great commentary on Microsoft's recent In-Context Learning (ICL) Paper. Good insights on how many shots are needed for "few-shot" prompting.
Cool paper from Microsoft. And it's on the very important topic of in-context learning. So what's new? Let's find out:
0
0
0
Different AI models have different strengths, weaknesses, biases, and safety profiles. Blending them to achieve an optimal user experience is nontrivial.
0
0
0
How important is Context Engineering to leveraging AI? Even humans can’t be intelligent without good context. Full stop. Read that again.
0
0
1
“What techniques are you using to customize your AI systems?" Amplify, a VC firm, surveyed 500 software/AI engineers. Here are the results:
0
0
0
Google DeepMind’s research found vector search hits a scalability limit due to fixed embedding dimensions, underperforming BM25 in most cases. Time to explore hybrid approaches.
Google DeepMind Finds a Fundamental Bug in RAG: Embedding Limits Break Retrieval at Scale Google DeepMind's latest research uncovers a fundamental limitation in Retrieval-Augmented Generation (RAG): embedding-based retrieval cannot scale indefinitely due to fixed vector
0
0
0
I have thought this for decades. You can read more here:
github.com
🧠Cognitive load is what matters. Contribute to zakirullin/cognitive-load development by creating an account on GitHub.
0
0
0
Amplify, a VC firm, surveyed 500 software/AI engineers. The primary AI use cases they found are below.
1
0
1
One way to know you’re early on a tech stack: the ‘official’ SDK is v0.3.0-preview.5. Welcome to .NET MCP Servers. :-)
1
0
1
In the blink of a cosmic eye, we passed the Turing test. ... And yet the moment passed with little fanfare, or even recognition. - Mustafa Suleyman
0
0
0