Searching for github repos with ai brand name author or co-authors should provide plenty examples. Single commit claimed as version 1.0 from a few months earlier with no changes since is another guaranteed way to identify one. I wish all slopcoders a very get a life already.
Fuck AI
"We did it, Patrick! We made a technological breakthrough!"
A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.
AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.
Find some specific markdown files on Github like agent.md or agents.md or claude.md. You'll get a big list in no time.
Also filter the repos who have huge readme with a lot of emojis.
A lot of local LLM front-ends are obviously vibe coded by LLM enthusiasts using their local models. You can also check for Claude.md or AGENTS.md in a repo.
While Rust is not my main language, I can understand it enough to compare it to well formatted Rust code, as well as will use Rust to showcase why natural language programming is bad and confusing even though we're taking keywords from natural languages (and let is a great example of that, especially how Rust uses it). I already seen Bun, and forgot about it🤪.
The problem with slop code is not superficial.
The game the machine is playing is " reproduce text that looks like all the other text you've seen before". As such the code will look good, read well, etc. The problem is that the problems are hidden. Incongruent logic between parts of the same program. Subtle "unintentional" behaviour. Bug fixes which force an outcome rather than remove a fundamental issue.
Apart from excessive verbosity it can be hard to see the issues.
Here's a PR that I thought was just a massive waste of time: https://github.com/rhinstaller/anaconda/pull/7074