> I think when LLMs first came out people thought they could just say something like, "Make a Facebook clone". But now we're realizing we need to be more exact with our requirements and define things better. That has always been the bottle neck in software.

This was substantially predicted by Fred Brooks in 1986 in the classic No Silver Bullets [1] essay under the sections "Expert Systems" and "Automatic Programming".

In it, he lays out the core features of vibe coding and exactly the experience we are having now with it: Initial success in a few carefully chosen domains and then a reasonable but not ground breaking increase in productivity as it expands outside of those domains.

[1] https://worrydream.com/refs/Brooks_1986_-_No_Silver_Bullet.p...

▲

steveBK123 5 hours ago | parent | next [-]

It's interesting how predictable some of this is.

The LLMs turn out fully formed clones of stuff for which there exists copious amounts of code openly searchable on the web doing the exact same thing.

LLMs require developer-like specification, task/subtask breakdown and detail where such example code already exists.

As a professional prior to LLMs, how many problems that you work on have many existing free solutions but you neglected to use that code and decided to spend days doing it yourself?

▲

bonesss 3 hours ago | parent | next [-]

Well put, and same challenge to a lot of these demos & LoC numbers: if you were a pro prior to LLMs, how many of these demos could you fully recreate if you ignored copyright?

I’ve often reimplemented things at work that exist elsewhere. If I could just copy & paste whole solutions from GitHub and change the branding/naming slightly, I could make curl in an afternoon.

▲

juvoly 4 hours ago | parent | prev | next [-]

So true.

I can only think of hobby projects, like writing yet another emulator, expression parser or media processor in a new language I'm trying to master.

In a professional setting, you would always diligently explore libraries and only implement your own if there is no suitable alternative.

▲

pton_xd 4 hours ago | parent | prev [-]

> how many problems that you work on have many existing free solutions but you neglected to use that code and decided to spend days doing it yourself?

Only when the existing free solutions are licensed with something like GPL. Now I can just say, write me a C webserver library similar to mongoose and I get the functionality without the license burden.

▲

repelsteeltje 4 hours ago | parent | next [-]

You might as well have ignored or removed the GPL notice. Running it through the LLM laundering gets you a "fork" of unknown origin, questionable quality. You're still potentially open to supply chain issues but the chain is obfuscated.

And you now own full responsibility for maintenance.

	▲	grepfru_it 3 hours ago \| parent [-]
		I just vibe coded a socks proxy because existing ones were too thick. And let me tell you, you are absolutely right. Go libraries I’ve never heard of, new implementations that has not been tested.. I think the word for this is YOLO

▲

juvoly 4 hours ago | parent | prev [-]

Indeed, no license burden but you get a maintenance burden instead.

	▲	pton_xd 4 hours ago \| parent [-]
		Well I'd get that either way if I write it myself. Also I was joking, I'd never do that; feels gross. But I suppose it is a legitimate "productive" use of AI.

▲

pjc50 4 hours ago | parent | prev [-]

"We've invented the silver bullet from the book 'No Silver Bullets'"

	▲	bonesss 3 hours ago \| parent [-]
		I read that as a programmer and, lol, you’re right. I read how that’ll read to VCs coming from Altman and Musk and, ow, the entire stock market just made sense for a second.