> Cool. How many "complete, fully working" products have you released?

Fully featured? One, so far.

I also worked on small backing services, and a GUI application to visualize the data provided by a backing service.

I lost count of the number of API testing projects I vibe-coded. I have a few instruction files that help me vibecode API test suites from the OpenAPI specs. Postman collections work even better.

And I'm far from an expert in the field.

What point were you trying to make?

If you are far from an expert in the field maybe you should refrain from commenting so strongly because some people here actually are experts.

So you have built a few small PoCs, does not tell us much.

> If you are far from an expert in the field maybe you should refrain from commenting so strongly because some people here actually are experts.

Your opinion makes no sense. Your so called experts are claiming LLMs don't do vibecoding well. I, a non-expert, am quite able to vibecode my way into producing production-ready code. What conclusion are you hoping to draw from that? What do you think your experts' opinion will achieve? Will it suddenly delete the commits from LLMs and all the instruction prompts I put together? What point do you plan to make with your silly appeal to authority?

I repeat: non-experts are proving to be possible, practical, and even mundane what your so-called experts claim to not work. What do you plan to draw from that?

No, experts are saying that vibe coding sucks. LLMs absolutely do vibe coding, and the output is shit.

> What point were you trying to make?

The point is that software developers can't evaluate their own work. (Especially the kind of n00b developers that use LLMs.)

You initially made wild claims about insane productivity gains that turned out to be just one small product and a lot of wasted time under scrutiny.

(Asking LLMs to write tests is a waste of time. LLMs can't evaluate risks, which is the only reason to write tests in the first place.)

Let's see it then.

A good trial would be pointing an LLM at Jira and telling it to finish the backlog.

> A good trial would be pointing an LLM at Jira and telling it to finish the backlog.

GitHub is already rolling out this feature.

https://github.blog/news-insights/product-news/github-copilo...