591 karma · joined January 10, 2026
I have a feeling that the best AI systems to come will, in fact, be a complete package like this: a harness, a DSL, and an entire package designed to produce certain outcomes cheaper and faster.
And producing that complete package is why software engineering will not be obsolete.
One of the first things I noticed when I moved to Ukraine in 2020 was that even the political jokes that you see on television have real highbrow wit and humor, which assume a high degree of literacy to understand. Even talking to some kids who were 14 years old, I was surprised at how they had memorized poetry in multiple languages and could write beautifully in cursive. You don't find that anymore in the West.
Sure, kids over here doomscroll themselves on TikTok as well, but they are not illiterate.
I operated as a one-man bootstrapped startup for many years. And now it's just one man plus AI, which has made me much more productive. It's pretty much fully AI-controlled, depending on how you define it. But I still consider myself the owner of my own startup. AI is not the owner.
And yes, as a person who runs a fully online one-person startup, I know that it is impossible to do everything online.
Here are some amazing positive outcomes which I think AI may bring us:
- the breakup of tech monoculture and tech monopolies as it becomes impossible to secure bloated overcomplicated operating systems and software due to never-ending vulnerabilities. Once Mythos/Cyber capabilities become mainstream I think the future of software is small, focused teams building high-quality, securable software in multiple jurisdictions. Monoculture software becomes inherently dangerous. Big bloated tech monopolies like Microsoft will collapse under their own weight. Like what is happening to GitHub right now.
- the ability for small teams to compete with multi-billion-dollar behemoths, and that is already happening right now.
- curing cancer and other scientific breakthroughs like Terence Tao’s use of ChatGPT
- a return to local trust-based networks because digital content can no longer be believed, and that is already happening. Any video can be disqualified as AI, which means people are going back to in-person networks to validate trust.
- you can just do things and learn anything. It's so much easier for me to learn almost any topic with AI-assisted content organization, retrieval, etc.
No, it's not possible to do most of the things you listed purely online without physical, in-person communication. Silicon Valley still hires engineers and drags them into their physical office in San Francisco, instead of hiring them remotely, because you can't even build a software company fully remotely, forget about a physical world factory or chemical plant. Even the so-called fully remote companies were built on a lot of in-person collaboration between a small founding team in the beginning.
Oops, shots fired. A direct attack on the vibe coded app market. Replit, Lovable, etc.
The real question here is: what features of a programming language make it a good language for Large Language Models? And how would you design a framework that’s not meant to be written or read by humans, only AI? That is a very interesting question to me. I theorize that LLMs are good at writing Elixir because it doesn’t have OOP concepts that require abstract models “in your head” (the LLM doesn’t have a head) and physical world metaphors that only humans have experience with. Instead Elixir’s primary tool is “pattern matching”, which works on literal text patterns instead of abstractions, and that’s what makes LLMs good at it. The question “what features of a language make it good for AI” is very interesting to me and I foresee a lot more research in this area.
> The only way it might hold here is if no one with access to the cutting edge models bothers to run your code through one while an adversary does. That seems highly unlikely, particularly for any well funded organization.
But since AI models are non-deterministic and the harness matters a lot, simply "running your code through one" doesn't guarantee you'll find all the zero days. An attacker can simply run a few more iterations or use a slightly more advanced harness, or increase the temperature level and they are likely to find zero days which the maintainers didn't.
Here’s an example: back in the 2000s, everyone was afraid programming was going to get outsourced to India or other countries. It didn’t happen, Sillicon Valley continues to spend billions to import engineers to work in person even though it’s 10x cheaper to hire remote outsourcers in India who are just as skilled programmers. Why do they spend 10x to move physical bodies to the office? Because it’s impossible to write good software without being in the physical context of the problem domain and team.
Similarly you cannot outsource to AI, because it cannot have complete context. No matter how good AI is, the problem is not mechanically solvable.
Even a human could not “manage complexity” if it’s not in the right context. This is not about AI vs. human capabilities.
The reason human judgement is necessary is not because it's "better". It's because the entire reason the business exists is to execute the human's judgement. There is no "right or wrong" way to build a startup if different paths are all profitable, but the human decides what they want to do.
Could Bun have survived and done well even if they didn't rewrite the codebase in Rust? Yes, it would've been fine. But the human decided they wanted Rust, that's a different path they chose with different tradeoffs. The AI has no skin in the game , no ownership, it doesn't belong to the AI. The AI only exists to serve the human. And if the human wants to make good decisions, inevitably they need engineering expertise (or an engineer) to weigh the decision.
More precisely, a "perfect solution" doesn't exist. It's all tradeoffs given your goals. Someone needs to make the decision: 1. which tradeoffs are worth given your goals 2. which goals are worth defining or redefining. And do that effectively, you need to understand the problem, which goes back to engineering.
And rewriting is just an example. There are tons of architectural decisions that need to be made every day in the building of advanced software. This is no "correct" way to do it that the AI can know in advance, it's a technical decision to be made by an engineer.
Neither 1 nor 2 can be done by someone who doesn't even know what Bun, Zig, or Rust is, let alone deeply understand how those work. In fact, even I as a programmer with decades of experience in PHP/Python/JS but without specific experience in Zig and Rust probably couldn't do a proper rewrite for a project the size of Bun.