This reads like a piece of content written a year ago. Things have radically changed since then.

"AI writes shallow tests" - used to be true, not true anymore since Astra and Fable 5.1 / Opus 5.5.

"AI writes overly complex ccode" - only if you let it. A "do not overengineer it" or "Pareto, 80% result with 20% of effort" go a long long way.

"Reliance on AI decreases human understanding" - human understanding does not decrease, it just moves up a level or two. The same way you do not really understand how the Linux kernel works, nor do you know how assembly really works (with probably a bunch of exceptions here given this is the HN crowd!). And then there is hardware and physics too.

Understanding code, algorithms and data structures becomes a rarer need than it used to be.

"AI moves too quickly to maintain a high quality bar" - if you are stuck with the mantra that humans must review the code today, then obviously that statement becomes true. The problem is the assumption, not the observation. The good news about AI progressing fast is that coding AND reviewing get better and better with each release.

I know it is tough to let go. But as a software engineer, the sooner you do it, the quicker you will learn to yield a much, much more powerful weapon.

> "AI writes overly complex ccode" - only if you let it. A "do not overengineer it" or "Pareto, 80% result with 20% of effort" go a long long way.

No doubt code quality increased substantially, but I've been wrestling overengineering for a long time, with both GPT/Claude - they will take any small chance to write excess code/documentation/specifications, anything - they seem to love reinventing the wheel. Heck, even prompts sent to subagents are walls of text.

Explicitly requiring simple solutions works for simple problems, but for more complex ones, complexity quickly creeps in. I even ask the alternative model to challenge the complexity of solution, but doesn't work really well.

There is a perverse incentive for AI companies to train models to be verbose, as it increases the tokens consumption.

> "AI writes shallow tests" - used to be true, not true anymore since Astra and Fable 5.1 / Opus 5.5.

You can also tell it what kinds of tests to write. (Assuming you're still interested in details of the codebase).

> "AI writes overly complex ccode" - only if you let it. A "do not overengineer it" or "Pareto, 80% result with 20% of effort" go a long long way.

Also, if it wrote a complex solution, tell it write a simple one instead.

In my experience, good AI adjusts pretty well to an existing code base, and produces roughly similar abstractions to the ones it finds.

Even 'technical debt' seems outdated... better models are coming that will fix the shortcomings of todays models.

> Things have radically changed since then.

No, AI is still absolutely terrible at design.

It doesn't matter if they are good at implementation.

If you ask for a car and they build you an awesome surfboard, it's basically worthless.

Sure, if you're building rapid prototypes where it doesn't matter if anything is coherent or works, AI crushes it.

If it's a 99% derivative small greenfield project, AI crushes it.

For anything real, it is still a painfully awful experience to extract juice from the squeeze.

And here we are back in 2024 prompt engineering stage of "you're not using it right." Wake me up when we get back to the loops and harnesses phase.

There have been spontaneous demonstrations amongst the workers voicing their joy and gratitude at our happy new way of life...

Blah, blah. They told us the same in 2025, 2024, 2023: "This is fixed in the latest frontier model!!!"