I run agentic AI workflows 8+ hours a day as my primary development environment.
Not experimenting. Not tinkering. Shipping production software — 4,000+ tests, 32 sprints, 225+ sessions.
Here's what peak AI-assisted development actually looks like 🧵
@elonmusk 91 days, 1930 commits, agentic business os with 93 production API routes, 6,044 automated tests, enterprise security all built and designed by my 8th Gen agentic software developement harness. Ai making Ai!
Is that the kind of complex problem solving you're looking for?
Great chat with Lex and Jensen. Ai is on the move! Pay attention and work hard.
The time is NOW!🌊
The limits of AI scaling laws - NVIDIA CEO explains | Jensen Huang and L... https://t.co/etEfuTDYWy via @YouTube
Today I run agentic AI workflows through Claude Opus every single day. Not as a hobby — as my primary development environment.
Prompt engineering. Multi-tool orchestration. Recursive systems that improve themselves every session.
This is my 9-to-5.
I run agentic AI workflows 8+ hours a day as my primary development environment.
Not experimenting. Not tinkering. Shipping production software — 4,000+ tests, 32 sprints, 225+ sessions.
Here's what peak AI-assisted development actually looks like 🧵
The future of work as we know it will end before we expect.
Now is the time to understand and grow the abilities necessary to harness and deploy artificial intelligence and robotics.
The future is autonomous and AI is at the center. We are at a pivotal moment in human history that we will never see the likes of again. Take advantage before the wave passes. It's no fun on the beach watching the surfers do their thing.
Optimus will be the biggest product ever made.
A general-purpose humanoid robot that can do useful work at scale will change the economics of labor & manufacturing.
Goal is to get Optimus to high-volume production as fast as possible.
If you’re great at AI, engineering, or manufacturing & want to build this, join us!
→ https://t.co/s3YW8Z6tZO
Most people use AI to autocomplete code.
I use it to orchestrate entire development cycles — architecture docs, implementation, test suites, deployment, quality audits — through a multi-agent system with governance, checkpoints, and recursive self-improvement built in.
This isn't exactly the right approach. Human in the loop means more than saying what the function is you want.
Proper governance comes from context. The AI software developer of the future knows who it's writing, what the software pain point overcoming target is, how to keep it simple, how to keep it secure and how to keep it efficient.
Larry Ellison just told every software engineer on Earth their job description is dead. Not evolving.
Dead.
Ellison: “The code that Oracle is writing, Oracle isn’t writing. Our AI models are writing.”
This is not a startup demo. This is one of the largest infrastructure monopolies on the planet telling you it already replaced the people who built it.
For fifty years, building software meant translating human intent into machine instructions. Line by line. Bug by bug. Sprint by sprint.
That entire layer is gone.
Ellison: “We don’t write the procedure. We declare our intent.”
That sentence just made the entire engineering labor market flinch. The procedure was the job. The procedure was the paycheck. The procedure was what made a developer valuable.
And now the machine does it without being asked twice.
Ellison: “We just tell the model what we want the program to do, and then the AI comes up with a step-by-step process to actually do it.”
You are no longer paid to build. You are paid to think.
And most organizations have no idea how to evaluate that.
The companies still hiring armies of developers to grind through codebases are paying salaries the machine already made worthless. Not in years. In seconds.
When a company worth hundreds of billions hands the keyboard to the machine and tells you the output is better, the debate is not winding down.
The debate is over.
The enterprise that wins this decade does not write the best code. It removes the human from the process entirely and runs on intent alone.
The programmers who survive are the ones who realize the craft is no longer typing.
It is architecture. It is judgment. It is knowing what to build and why.
Everything else now belongs to the machine.
And the machine does not negotiate severance.
I see people talking about how their job wont be impacted by robotics and automation.. I wonder why people think this an the only answer I can come up with is that they are simply unaware.
This is exactly why I chose to partner with the technology. There are few other ways to interact and participate in the future economy and I want to position for success at the front of the wave, not after it's passed.