[bitwize]

There are companies building entire applications, indeed replicating the functionality of existing SaaS applications to test their original applications,with no humans in the development loop.

We're looking at the twilight of programming as a human skill. The LLMs are just that good.

[rwyinuse]

The end result is, and will always be garbage if there is no "human in the loop" to test whether the result meets the requirements, and telling LLM what to do if it doesn't.

Like somebody else said, there is still a need for QA (and usually for requirements gathering too), that's a part of the development cycle. Developing software that is meant to be used by humans with zero humans involved isn't realistic.

[scuff3d]

I mean... It takes 10 minutes of testing to know this is bullshit. At least in the near term. I've sat with an agent and played the part of a vibe coder. Not looking at the code, frankly providing more guidance and feedback then a vibe coder could, and even in a thousand line app it falls to absolute shit fast. It does get something that "technically" works, but it will collapse in on itself in no time.

The act of designing software might be changing, less writing the actual code, but someone who knows what the fuck they're doing still has to guide the ship.

[bitwize]

"Vibe coding" with a single agent is really only a thing for small-scale projects. Really you want to be orchestrating many agents: some generating code, some reviewing, and some testing, feeding back into the generators. Cloudflare developed a clone of Next.js this way and are putting it into production. No humans in the main development loop.