Stoat removes all LLM-generated code following user criticism (github.com)

What a shame

It seems the thread was brigaded by militant anti-AI people upset over a few trivial changes made using an LLM.

I encourage people here to go read the 3(!) commits reverted. It's all minor housekeeping and trivial bugfixes—nothing deserving of such religious (cultish?) fervor.

Looked at repos of the two loudest users in that thread; either they have none or it's all forks of other projects.

Non-contributors dictating how the hen makes bread.

Wastes of time like this are exactly why Stoat/Revolt is unlikely to ever be a serious Discord alternative

If only the average open source project got this level of scrutiny actually checking for vulnerabilities. I get that you don't want your private chats leaked by slopcode, but this was a few dozen lines of scaffolding in large software created before LLM coding; it would have been better to register your discontent without making demands, then continue to watch the repo for vulnerabilities. This feels like fervor without any work behind it

Reverting a few trivial commits because of purity tests is a bad precedent. It rewards the loudest commenters and punishes maintainers.

Nice move! It is fun to watch the copyright thieves and their companies go into intellectual contortions (militant, purity tests, ideology) if their detrimental activities get any pushback.

The fun part is this only happens because Claude Code commits its changes.

If you use for example, GitHub Co-Pilot IDE integration, there's no evidence.

"it's worth considering that there are many people with incredibly strong anti-LLM views, and those people tend to be minorities or other vulnerable groups."

I have pretty low expectations for human code in that repository.

I love how people in the thread are like "if I'm going to ask my group of friends to switch to this, I need to know it's not written by security-issue-generator machines", meanwhile at Discord LLMs go brrr:

https://discord.com/blog/developing-rapidly-with-generative-...

If you find yourself having to use LLMs to write a lot of tedious code, you have bad architecture. You should use patterns and conventions that eliminate the tedium, by making things automagically work. This means each line of code you write is more powerful, less filler stuff. Remember the days when you could create entire apps with just a few lines of code? So little code that an LLM would be pointless.