Hot is hot. Gender, race, etc. isn’t a factor.

Good coverage is still a lot better than no coverage when doing changes in a project you haven’t touched in ages

A 20€ plan of Claude Code for a month will teach you all of it.

It’s pretty much just scripting ffmpeg and feeding the screenshots to a local model via an API (or use a CLIP model)

I have a script that uses yt-dlp to get subtitles off a YouTube video and summarises the main points for me with a language model so that I don’t have to watch a 20 minute top10 list video that could’ve been a buzzfeed article.

The whole thing is fully vibe engineered too.

I built a system that translates subtitles from English to my native language and it beats cheap-ass “official” translations 9/10

It even gets colloquial terms and phrases right, adapting to the correct song for example - something a human translator working for minimum pay usually won’t bother

Multimodal local models like qwen3.5 are pretty good

Basically you grab screenshots from the video at intervals and ask the model to tag / describe them.

ChatGPT is pretty good at “what was that thing where…” type of stuff and usually gets it on the first go

The search engine integration in Safari is a bit janky, but otherwise everything is peachy

If you’re secure in your heterosexuality, you can be a bit gay sometimes 😎

My LLM slop personal projects have better test coverage than many many many professional projects I have had the “pleasure” of working with.

A dude who once tried plain water and almost puked because it didn’t cover the vile taste of his rotting teeth.

Oh and he’s an actual millionaire who lives in a trash heap