[deweller]

"Developers talk not just about how the AI output is often flawed, but that using AI to get the job done is often a more time consuming, harder, and more frustrating experience because they have to go through the output and fix its mistakes."

This has not been my experience. Sure it feels like more work to fix the AI code problems sometimes - it is a different skillset than writing code from scratch. But the speed that I can deliver software has significantly increased by using coding agents.

[munksbeer]

I must be doing something very different from the anti-AI people on here. It is ridiculously empowering.

Got an issue in production? Give your agent the knowledge of how to locate the logs, and where the codebase is, and ask it to diagnose, and off it goes. It almost always finds the issue, and while it has been doing that, I've been able to get on with more productive things.

In terms of coding, if you work on it, and give it the correct guidelines, guardrails and ability to check its own work, it produces very high quality results.

The worst part is in such a short space of time I just don't think I can ever back to normal coding. I don't mind that, but it sucks when I'm offline.

I honestly don't know what people are doing wrong, or what sort of code they're writing that they can't get an AI to work well for them.

[MintPaw]

There's just different types of programming, I also find that if I give a decent description of a bug an LLM will often find the problem, and that great in a system that's mostly legacy and hard to repro. LLMs are also good for quick small scale from-scratch projects.

But there's a middle ground where you're really have to build something out that's super complicated and performant. Or do refactors that have a high quality bar. Situations where code bloat really matters. LLMs tend to create crazy amounts of code, not really thinking through the broader system and taking system level in-variance constraints seriously.

[deweller]

This is also my experience 80% of the time.

Now that I am used to this, the other 20% feels like a lot more work than it used to. Is it more work? No. But my expectations have changed.

[rkozik1989]

Honestly, the effectiveness of LLMs in coding depends a lot on what you're working on. If you're dealing with a software package like Odoo that's been around for literal decades an LLMs output can be borderline useless. The problem is that in its training data it has examples from every version that's ever been released and each succeeding major version makes breaking changes to the previous one, so pretty much what happens is that the LLM can't accurately tell what in its training data belongs to which version before concocting a reply.

[jjulius]

>This has not been my experience.

>But the speed that I...

[bensyverson]

First-hand experience is perfectly valid.

I agree with the parent; I'm able to produce more. And with proper documentation and unit tests in place, I don't feel I need to review every line.