bilater

All -

I’ve been wanting to use Jev in a project, and I recently saw Firecrawl use it in an interesting way. They use their crawler to pull company data and then use Jev to classify the companies into categories. I thought this was a very powerful way to gain insights out of publicly available data, so I tried it on Hacker News.

I pulled every comment and post since 2008 that asked for some piece of software or a tool (~63k of them). Jev kept the 12k that were real requests, for about $6 (on OpenRouter). Opus 5.5 grouped those into concrete tool ideas and re-read every request behind the top 100.

Finally I checked Show HN to see which ones already exist. Still a few left to build, in case you’re looking for an opportunity :D

Actually, I think the lesson from this article is that a lot of these little hacks we’re doing around context compaction, AGENTS.md, system guides, and other harnessy ways of saving tokens are going to go away fairly quickly, just as all the tricks of the telegraph era went away once communication got cheap enough that it was easier to just speak in plain language.

No, I am engaging with the point: centering human achievement over something potentially greater is lowering the rim. There is nothing special about humans.

Again, the assumption that forms the crux of these objections of all of these is that we're going to hit some plateau where we are going to need humans to come back in, reskill, retake over, etc. I don't think most people are prepared for the fact that that's just a midwit problem and the AI will just keep getting better and won't need humans in the loop.

It's not okay to ask the world to slow down so you may catch up. It's not okay to ask for the rim to be lowered so you can dunk. Instead, ask how you can get faster, how you can get stronger, and actually get the ability to dunk.