Isn’t having humans review every PR only realistic for smaller systems? If AI is generating all these PRs, but humans still have to review every one of them, doesn’t that ultimately leave the humans responsible for everything?

Someone has to be responsible, because it sure won't do to call Anthropic at 4 am and ask why Claude caused your service to rack up $5m on AWS and delete all backups.

Quake is still around. It's a nostalgic game from decades ago, but I'm surprised it still exists

Great read. I was already familiar with the overall concept, but the step-by-step, chronological explanation made it much easier to understand.

Highly recommended for infrastructure engineers, solution architects, and developers.

AI only does what it is instructed to do. Without deep domain knowledge, results produced from simple prompts alone cannot be turned into production-ready products. In reality, creating detailed prompts, conducting continuous reviews, and providing iterative feedback after the prototype stage often takes even more time than building the prototype itself.

If people manage their own data, that essentially means each person has their own database. And a database has to be connected to an application. Whenever the database schema changes, the application's CRUD operations have to be updated as well.

In the end, it seems likely that everyone will develop and maintain their own web application, and if others need access to their data, they'll expose it through APIs.

I enjoy studying different refactoring patterns and real-world examples.

DeepSeek is great for tasks and software I already know well. Even if it gets something wrong, I can usually verify it myself. But when I'm working with a programming language I'm not familiar with, I prefer using Codex or Claude.

Yeah, it needs quite some hand holding.

I didn't do much agent coding and had a mix experience.

1. It would build something that was in the spirit of what I wanted, but unusable in practice.

2. It would build something quite useful, but only the public APIs were nice, the deeper code layers would get more and more convoluted.

3. It would built what I wanted and it would have okay-ish code.

However, for 3. I also had to add a custom AGENTS.md, many more code example, extra repos as subtrees, and review any code that had new concepts.

Much more work, but still much less than typing it all by hand.

I think it's a matter of personal privacy. You shouldn't show it to other people.

I'm not sure whether Chinese AI models are being banned because of concerns about corporate data leaks, to slow China's AI development, or to protect the U.S. AI industry. But for startups, I think affordability is probably the most important factor.

China's strategy has always been the same: copying and low-price competition. It's the most efficient way to gain market share.