Not my experience at all. Quite the opposite. At my workplace we use AI to improve code quality and software design every day, far more than we used to, because AI makes it fast and easy.

I’m not convinced code reviews add much value, unless most of your co-workers are less capable and you’re trying to improve overall quality.

That said, I get a lot of value from talking to experienced developers before writing any code.

> I've also tried to understand the code that AI writes, but it's often insane and untangling it would slow me down

I hear that a lot, but it is very different from my experience using Claude Code every day. The code it generates is pretty much what I would have written myself. My colleagues have always said my code is easy to read and understand, so hopefully it is not just because my code is insane too :)

So I wonder: how are you using LLMs?

> and so has the output quality

Not my experience at all. The quality has gone up dramatically. Because we also use LLMs to make large scale refactorings that cleans up the code and use it to find lots of bugs that would otherwise have exploded in production at some point in time.

I just used Fable to thoroughly review a PR, and it came up with 5 "Findings that block approval".

I went through each one through the code path (a couple were already considered during implementation), and while all 5 were theoretically accurate, 0 of them were actually reachable.

I wrote them back to Claude point by point and got this back: "I checked all five claims against the code. Your list is correct on all five. I downgrade my verdict: none of the five findings blocks approval. Details and one subtlety below."

This is a usual experience with SOTA models for me and others in my team.

Don't get me wrong, I use it daily; sometimes as a crutch, other times as an accelerator, mostly as a validator/peace of mind. I however don't think that neither velocity or quality is meaningfully changed. But I do spend much more time arguing with a machine.

That is interesting. I use Opus 5 as my daily driver, and it pretty much just works.

For example, a few weeks ago I asked it to analyse my code and find duplicated code that could be extracted into reusable libraries. It found several good examples and did the refactoring. I reviewed the result, and it was 100% how I would have coded it myself.

I do almost no manual coding these days. Opus 5 just works for me.

So it is strange for me to read comments like yours saying that it doesn't work. It would be interesting to find out what makes the difference?

Me too, because I hear a lot of experiences like yours as well. It might be opinionated architecture not fitting the training norm, size of legacy repos/projects, language, or whatever else.

For what it's worth I/we do much less manual coding now too, but it almost always takes a handful of re-prompts to reach expectations.

We can do hooks to reduce superfluous comments or do a second specs-adherence pass, or write failing tests first, but other discrepancies aren't uniform enough to enforce in prompts or context.

I'd love to know the difference too. Or whether long term velocity would be higher by vibing through PRs and deal with issues when things explode or refactor down 2M lines of LLM creep after the fact.

This!! the amount of times that has happened to me in PR. A lot of the times its my fault as I haven't given the agent all of the context ( sometimes intentionally to cross check if it would reach to the same conclusion as me without additional info) but as soon as I give it all the context it would then back track on most of the blockers.

It's interesting how different your experience is from mine. I would love to find out why it works so well for me but not for you.

I use Opus 5 every day, and it just works. It is very rare that I need to do any manual editing.

I would cry a lot. I love my Claude Code :)

But other than that nothing really.

I can't remember what I wrote yesterday. So it forced me from an early age to not write spaghetti code. Which is a real advantage it turns out when working on large projects. And an even bigger advantage when using LLM's to code.

The platforms unfortunately have zero incentives to help you manage your addictions to the "wrong" things. Quite the opposite.

The same way bakeries and cafes have zero incentives to not be your local sugar addiction dealer.

Marx was extremely simple minded when it came to human nature. That’s the problem with all utopian ideas and all idealistic philosophers and economists: the assumption is always that humans will behave in some idealised way. While in reality greed, cruelty, corruption, treating other humans as inhuman or slaves is part of human nature. Not the only part of course, but probably the most important part when looking at the very long list of disaster we call history.

Not at all. High level objectives from above are transformed and interpreted and subdivided by lower levels into actual planning and execution.

Also, a corporation is infinitely more simple to manage than a whole country.