[123yawaworht456]

there are several AI features I would absolutely love to see integrated into the browser, primarily, content filtering with my own custom criteria.

for example, I don't want to see yuppie shit on news.ycombinator.com. right now, I have a userscript that filters out links from the worst offenders (e.g. newyorker), but every day, there are many more that shit up the front page and waste my time and attention. this could be solved with a very low parameter LLM by asking it to evaluate whether the text is related to science and technology or not.

hell, even images could be filtered with vision models, including local ones. I'd fucking love to hide a few broad categories of images from my sight, e.g. clickbaity youtube thumbnails (DeArrow helps to a degree)

[lupusreal]

> for example, I don't want to see yuppie shit on news.ycombinator.com. right now, I have a userscript that filters out links from the worst offenders (e.g. newyorker), but every day, there are many more that shit up the front page and waste my time and attention. this could be solved with a very low parameter LLM by asking it to evaluate whether the text is related to science and technology or not."

FWIW, I once used naive Bayes classification solely on HN headlines and it worked reasonably well for solving the problem you're describing.

[everdrive]

This is just an arms race. It expends more energy, and the "solution" from the other side will be to pump more garbage in.

[123yawaworht456]

you could save even more energy by not using computing devices at all.