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
Nice work putting this together! But also, we're entering an era where folks might easily be able to scratch their own itch for many of these needs :-)
Explains the shallowness of the analysis, most of which are not products, and confirms my intuition that Jev is way over hyped and not capable of the things people claim it is. Give it a coin flip for the simplest example.
Love Hezner amd how cheap they are for the services they provide. I'm building a "roll your own Vercel" on top of it. It's gonna be open source full self hosted or a semi-managed (bring your own Hetzner server and pay for some sugar on top) service. Appreciate any feedback!
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.
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.
Your response completely misses the point the author is making, which I find a really common attribute among AI evangelists looking to earn a quick upvote.
The author isn't asking the world to "slow down" or "lower the rim"; they're asking the world to reevaluate its priorities and re-center human achievement over raw output. If you want to disagree with that request, that's one thing, but do it by engaging with the author's actual point rather than inventing a different one that you think you can dunk on.
No, I am engaging with the point: centering human achievement over something potentially greater is lowering the rim. There is nothing special about humans.
Ah yes, I hadn't considered that generating materialist slop to make (certain) bank account numbers go up might be a higher cause than anything else the dominant sentient life form of the planet stands to gain from not doing that. How foolish of me. I've been such an idiot.
I've struggled with this question as well, and this is why I reject the premise of the historical pattern of technology enabling us to "move up" to something else.
At the same time, I agree with the original comment as well. I don't think this necessarily leads to some doomsday scenario. Whatever happens it'll likely be better for us and imo we will merge with the AIs at some point, so it won't be a question of us vs them.
I actually see it more likely the opposite - a subset of humans will retreat into a (vastly smaller) human-first world, and AI will be of a separate world concerned with material/scientific/research concerns and appeases the masses who are still around.
We can already see this today in the form of upper class parents (like myself) who vastly restrict their kids screen time and ban social media. We may see AI-free societies that form, but supported by AI. The jobs and roles people play within that society may deal with services that really need to be done by a human, being a buffer from AI to the rest of this society, or just straight up fake.
I personally think this is close to a doomsday scenario - but it doesn't end with a big bang, but more of slow quiet death.
I figure both will happen. Some people will want to live naturally, some to merge. I sometimes think with the data centers in space discussion that it'll end up with AIs in space and the Earth as something like a nature reserve.
I think many people will be quite content not merging with AI and having AI do everything for them. Perhaps only a small subset of people will want to merge with AI. They may not be allowed to though, if majority of people fine not merging then they may ban those who want to merge.
The subset of people who will want to merge will be people who will not be content with having no control over their future. No ability to create new inventions, new discoveries, new ways of working. They will not be content with just having everything provided to them, playing the social games that will remain and think their environment is a prison.
Only if you have a zero-sum game mindset. I suppose it does make sense that AI-native intelligences are just smarter than hybrid AI-human entities (biologically enhanced or uploads) but that doesn't mean there needs to be conflict between the two. The universe is huge. :)
I personally don't think there will be a conflict, but more just an extinguishing of all things human, outside of niche forms of entertainment and care. It won't be machines that cause the conflict, but the frustrated and bored masses fighting over the scraps left behind by the machines and ultra-wealthy.
https://stillunbuilt.shiptiffin.app/
reply