I can imagine that works for most cases, but when you try to include some lesser known and obscure library, that is heavily typosquatted, you might run into issues.

At this point I’m seriously considering just running something like openclaw with a basic model to just keep clicking on random stuff and browsing the internet, changing personalities each day at random, to flood my IPs data.

This will be a goldmine for malware groups that are poisoning AIs that use web search to get them to use their malware-ridden version of software and libraries, and I’m here for it with popcorn at the ready.

I kinda hope this will get more common, because the only people affected kind of deserve it, plus it’s a great way how to filter sloprojects at a glance.

This kind of does something similar :D https://codeberg.org/TheMikina/git-llmfs

While I’m not a fan of most AI usages, this is the thing that infuriates me the most.

I like writing scripts to automate parts of my job. I’ve had a few for things like build performance testing comparison and the like.

All of it was replaced by skill.md, that does exactly the same, but burns like 3$ per run in tokens, and has also at least once generated hallucinated results, because it ran into an error, ran wrong builds, or in general fucked up in a way that was not easy to detect (and we did in fact not detect it until much later).

But hey, at least my colleagues now don’t have to open the filthy commandline and write py perf-test.py main feature/branch to run the test, and can just talk about it to a clanker.