Ron Clabo

Tweets about software development: .NET, AI, ASPNET Core, C#, Agentic Coding, & LuceneNET. Top 1% on StackOverflow. I Love learning & helping others.

[David Fowler @davidfowl]

Been using this for ~2 weeks and it's absolutely changed my workflow and tokenmaxxing 😄.

#github #copilot

[Avid @Av1dlive]

Garry Tan (CEO of Y-Combinator): "when someone asks how I 'prompt' my AI, the answer is: I don't. the skills are the prompts."

[if I had 7 days to master skills and how to use them to automate workflows:]

→ read the Skillify 11-item checklist (SKILL.md in gbrain)
→ watch Murag + Barry Zhang: "Don't Build Agents. Build Skills Instead."
→ Read "Designing, Refining, and Maintaining Agent Skills at Perplexity"
→ do one workflow. type /skillify. watch it become permanent.

that's the whole day.

here is how to set it up:

1. clone GBrain (his open-source second brain, Postgres-backed memory + 30 skills)

2. add GStack (23 battle-tested slash-command skills, drops right in)

3. do anything once → type /skillify → it's a skill forever

prompting is dead. skillifying is next.

[Ron Clabo @dotnetcore]

An example where GPT-5.5 is ~39% cheaper than Opus 4.7 even considering it's more expensive output token costs.

[rahul @rahulgs]

GPT-5.5 is ~39% cheaper than Opus 4.7, across merged PRs bucketed by diff size in Inspect

despite the higher output token cost, 5.5 is cheaper for input tokens (cache writes are free), more token efficient, and tokenizes the same text to fewer tokens

[Gergely Orosz @GergelyOrosz]

Prediction:

The next 12-24 months, "UX-pilled" builders will be in massive demand.

Who can create intuitive interfaces, web+mobile+desktop apps that "feel good," natural, fast, and far better than the competition.

THIS will be the difference vs those building "just" with AI.

[Ron Clabo @dotnetcore]

Feeling like it's time to jump into AI enabled software development? Microsoft just launched a free GitHub Copilot CLI course.

There has never been a better time to be a software engineer.

[.NET @dotnet]

We just launched a free, open-source course on GitHub Copilot CLI.
Learn how to ship faster with AI powered command line workflows—context, custom agents, skills, MCP servers, and more.
Hands on. Practical. Built for devs.

Check it out: https://t.co/gFBNFUcwfG

[Ron Clabo @dotnetcore]

@TheTuringPost Great article. Excellent points. This feels like process automation from the 1990s all over again.

[Ron Clabo @dotnetcore]

An API on track to do $1B in revenue. That was unthinkable just a few years ago. Welcome to the age of AI.

[Greg Brockman @gdb]

gpt-5.4 has ramped faster than any other model we've launched in the API: within a week of launch, 5T tokens per day, handling more volume than our entire API one year ago, and reaching an annualized run rate of $1B in net-new revenue.

it's a good model, try it out!

[Ron Clabo @dotnetcore]

@kermitv Yep, lots of fun to watch.

[Ron Clabo @dotnetcore]

#GTC26 keynote is live. It's such a joy to watch. There is only one Jensen Huang and only one NVIDIA.
https://t.co/lrYQeF5Izo

[Ron Clabo @dotnetcore]

NVIDIA's AI token performance is truly astounding.
#GTC26 keynote.

[Ron Clabo @dotnetcore]

I realize this is NOT enterprise class software. But this should be a wake up call to all developers who think their job won't seriously change in the age of AI.

[Lena Hall ✈️ NYC @lenadroid]

This is wild 🤯

My 5-year-old just built his FIRST GAME ever with Codex using only dictation mode.

He wanted a game where you type in a word and transform into any character you want to be ✨ so he dictated it to Codex.

Then he upgraded it to a game where that character jumps and collects coins.

Hello World to the youngest AI engineer ever❤️‍🔥 @OpenAI @OpenAIDevs

Codex needs an interactive voice mode ASAP

[Ron Clabo @dotnetcore]

I really appreciate this down-to-earth article on how to better use agents to write code, whether Claude code, Codex CLI, Gemini CLI or whatever. Very practical advice, no fluff.

[sysls @systematicls]

https://t.co/wBaKpAI5Vl

[Ron Clabo @dotnetcore]

1M lines of code AI written from scratch in 5 months: https://t.co/AOGfWwwM7e

[Ron Clabo @dotnetcore]

OpenAI reports running a 5-month experiment: ship an internal beta with 0 lines of manually written code.

Application logic, tests, CI, docs, observability, tooling — all generated by Codex.

Humans steered. Agents executed.
Result: ~1M lines, ~10x faster than hand-coding.

[Ram Maheshwari @rammcodes]

Sonnet 4.6 inside VS Code 🤘

Just 1–2 hours after launch, Sonnet 4.6 was already available in GitHub Copilot Chat. That rollout speed is kinda crazy :)

Hope this helps ✅️

Follow @rammcodes for more 💎

#html #ai #javascript #coding #webdevelopment #programming

[Ron Clabo @dotnetcore]

Impact of AI on Software Devopment
TL; DR:- Monoliths return; Strongly typed languages rise; Open source restructures around Agents; optimal LLM programming languages may look nothing like what humans use

[Thomas Wolf @Thom_Wolf]

Shifting structures in a software world dominated by AI. Some first-order reflections (TL;DR at the end):

Reducing software supply chains, the return of software monoliths – When rewriting code and understanding large foreign codebases becomes cheap, the incentive to rely on deep dependency trees collapses. Writing from scratch ¹ or extracting the relevant parts from another library is far easier when you can simply ask a code agent to handle it, rather than spending countless nights diving into an unfamiliar codebase. The reasons to reduce dependencies are compelling: a smaller attack surface for supply chain threats, smaller packaged software, improved performance, and faster boot times. By leveraging the tireless stamina of LLMs, the dream of coding an entire app from bare-metal considerations all the way up is becoming realistic.

End of the Lindy effect – The Lindy effect holds that things which have been around for a long time are there for good reason and will likely continue to persist. It's related to Chesterton's fence: before removing something, you should first understand why it exists, which means removal always carries a cost. But in a world where software can be developed from first principles and understood by a tireless agent, this logic weakens. Older codebases can be explored at will; long-standing software can be replaced with far less friction. A codebase can be fully rewritten in a new language. ² Legacy software can be carefully studied and updated in situations where humans would have given up long ago.

The catch: unknown unknowns remain unknown. The true extent of AI's impact will hinge on whether complete coverage of testing, edge cases, and formal verification is achievable. In an AI-dominated world, formal verification isn't optional—it's essential.

The case for strongly typed languages – Historically, programming language adoption has been driven largely by human psychology and social dynamics. A language's success depended on a mix of factors: individual considerations like being easy to learn and simple to write correctly; community effects like how active and welcoming a community was, which in turn shaped how fast its ecosystem would grow; and fundamental properties like provable correctness, formal verification, and striking the right balance between dynamic and static checks—between the freedom to write anything and the discipline of guarding against edge cases and attacks. As the human factor diminishes, these dynamics will shift. Less dependence on human psychology will favor strongly typed, formally verifiable and/or high performance languages.³ These are often harder for humans to learn, but they're far better suited to LLMs, which thrive on formal verification and reinforcement learning environments. Expect this to reshape which languages dominate.

Economic restructuring of open source – For decades, open-source communities have been built around humans finding connection through writing, learning, and using code together. In a world where most code is written—and perhaps more importantly, read—by machines, these incentives will start to break down.⁴ Communities of AIs building libraries and codebases together will likely emerge as a replacement, but such communities will lack the fundamentally human motivations that have driven open source until now. If the future of open-source development becomes largely devoid of humans, alignment of AI models won't just matter—it will be decisive.

The future of new languages – Will AI agents face the same tradeoffs we do when developing or adopting new programming languages? Expressiveness vs. simplicity, safety vs. control, performance vs. abstraction, compile time vs. runtime, explicitness vs. conciseness. It's unclear that they will. In the long term, the reasons to create a new programming language will likely diverge significantly from the human-driven motivations of the past. There may well be an optimal programming language for LLMs—and there's no reason to assume it will resemble the ones humans have converged on.

TL; DR:
- Monoliths return – cheap rewriting kills dependency trees; smaller attack surface, better performance, bare-metal becomes realistic
- Lindy effect weakens – legacy code loses its moat, but unknown unknowns persist; formal verification becomes essential
- Strongly typed languages rise – human psychology mattered for adoption; now formal verification and RL environments favor types over ergonomics
- Open source restructures – human connection drove the community; AI-written/read code breaks those incentives; alignment becomes decisive
- New languages diverge – AI may not share our tradeoffs; optimal LLM programming languages may look nothing like what humans converged on

¹ https://t.co/0gO5TUwguU
² https://t.co/oN0PnPr1dF
³ https://t.co/nWKSw0m2Ct
⁴ https://t.co/ZrH3fhzQD4

[Ron Clabo @dotnetcore]

Coolest C# project I've heard of in a while. MicroGPT in C#

[Dr Milan Milanović @milan_milanovic]

I wanted to understand how GPT works, so I ported Karpathy's https://t.co/5FK9fuhDBF to C# from scratch. No frameworks and NuGet packages, just plain math in ~600 lines of code.

It builds a tiny GPT that learns from 32K human names and invents new ones. Every piece is there: autograd, attention, Adam optimizer, the works. Just at a scale you can actually sit down and read.

I also wrote a prerequisites guide that walks through all the math and ML you need, starting at a high school level. If you've ever wanted to peek under the hood of ChatGPT without drowning in linear algebra textbooks, this might help.

https://t.co/rwAB7pswzY

[Ron Clabo @dotnetcore]

"95% of the engineers use Codex, and engineers who embrace these tools open 70% more pull requests than their peers, and that gap is widening over time"
- Sherwin Wu, Head of Engineering, OpenAI Platfrom

[Lenny Rachitsky @lennysan]

My biggest takeaways from @sherwinwu:

1. AI is writing virtually all code at OpenAI. 95% of the engineers use Codex, and engineers who embrace these tools open 70% more pull requests than their peers, and that gap is widening over time.

2. The role of a software engineer is shifting from writing code to managing fleets of AI agents. Many engineers now run 10 to 20 parallel Codex threads, steering and reviewing rather than writing code themselves.

3. The average PR code review time has dropped from 10-15 minutes per PR to 2-3 minutes. Every pull request at OpenAI is now reviewed by Codex before human eyes see it, and Codex surfaces suggestions and catches issues up front. This allows engineers to focus on more creative and strategic work while dramatically increasing productivity.

4. The models will eat your scaffolding for breakfast. When building AI products, don’t optimize for today’s model capabilities. The field is evolving so rapidly that the scaffolding (vector stores, agent frameworks, etc.) that seems essential today may be obsolete tomorrow as models improve.

5. Build for where the models are going, not where they are today. The most successful AI startups build products that work at 80% capability now, knowing the next model release will push them over the line.

6. Top performers become disproportionately more productive with AI tools. AI tools amplify the productivity of high-agency individuals, so the gap between top performers and everyone else is widening. The ROI on unblocking and empowering your best people compounds faster than ever in an AI-augmented environment.

7. Most enterprise AI deployments have negative ROI because they’re top-down mandates without bottom-up adoption. Success requires both executive buy-in and grassroots enthusiasm. Sherwin recommends creating a “tiger team” of technically-minded enthusiasts (often not engineers) who can explore capabilities, apply AI to specific workflows, and create excitement throughout the organization.

8. The one-person billion-dollar startup is coming, but with unexpected second-order effects. As AI makes individuals more productive, we’ll see not just billion-dollar solo founders but an explosion of small businesses: hundreds of $100M startups and tens of thousands of $10M startups. This will transform the startup ecosystem and venture capital landscape.

9. Business process automation is an underrated AI opportunity. While Silicon Valley focuses on knowledge work, most of the economy runs on repeatable business processes with standard operating procedures. There’s massive potential to apply AI to these workflows, which are often overlooked by the tech community.

10. The next two to three years will be the most exciting in tech history. After a relatively quiet period from 2015 to 2020, we’re now in an unprecedented era of innovation. Sherwin encourages everyone to engage with AI tools and not take this moment for granted, as the pace of change will eventually slow.

11. AI models will soon handle multi-hour tasks coherently. Today’s models are optimized for tasks that take minutes, but within 12 to 18 months we’ll see models that can work on complex tasks for upward of six hours. This will enable entirely new categories of products and workflows.

12. Audio is the next frontier for multimodal AI. While coding and text get most of the attention, audio is hugely underrated in business settings. Improvements in speech-to-speech models over the next 6 to 12 months will unlock significant new capabilities for business communication and operations.

[Ron Clabo @dotnetcore]

"A small team armed with AIs can move mountains"
It's an exciting time.

[Yuhuai (Tony) Wu @Yuhu_ai_]

I resigned from xAI today.

This company - and the family we became - will stay with me forever. I will deeply miss the people, the warrooms, and all those battles we have fought together.

It's time for my next chapter. It is an era with full possibilities: a small team armed with AIs can move mountains and redefine what's possible.

Thank you to the entire xAI family. Onward. 🚀

And to Elon @elonmusk - thank you for believing in the mission and for the ride of a lifetime.

[Ron Clabo @dotnetcore]

"LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building." Very interesting insight.

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.