Hacker Newsnew | past | comments | ask | show | jobs | submit | emehex's commentslogin

Claude Code and/or Codex from Ghostty/Terminal. You don't need to complicate it.

I think you'd be surprised to learn how many real production apps are actually running on top of SQLite (by way of Cloudflare D1).


Many DB servers are built upon embedded DB primitives (like RocksDB), that doesn’t mean the primitives are sufficient on their own.


I'm not sure what this has to do with my comment? D1 is pretty much sufficient on it's own...


My point is D1 is not sqlite, it’s a serverized architecture of it, including building things like replication, etc.

Plus, D1 has a 10gb limit which is wild to call “sufficient”.


This is like the anti-Cybertruck. But in a funny horseshoe kinda way the exact same as the Cybertruck?


I still do this for my dog every year on his birthday. Funny that the Pet Store survived the Internet while the Toy Store did not...


I do the same!

I’d guess one reason is that there has been no iPad/App Store/YouTube invented for dogs…

I have a gut feeling there will be negative consequences for how much time developing minds spend consuming but in the absence of clear cut evidence it seems to be the default.


Demographics play into the problem too. Massive decline in number of kids


I don't understand UBI.

Let's say a burger costs $10. Then UBI is implemented. But not just like $1K/month UBI... $1M/year UBI... for everyone! There's no way that the burger is still $10 now. Right?

Won't the economy just soak up all the extra UBI money? So a burger will cost $1000 in world where everyone gets $1M/year? And like $20 when everyone gets $1K/month? Isn't it all just a wash?


UBI in a world where everyone makes roughly the same amount of money per year would be a wash. You'd just be redistributing money to people in roughly the same percent that is was taxed from them. But we do not live in that world.

And even if it does end up as a complete wash, that still seems like it would lead to a better economic outcome. You'd end up with trickle-up economics. The kind that has incentives for companies to appeal to consumers, and consumers that have money to spend on goods and services.


> The kind that has incentives for companies to appeal to consumers, and consumers that have money to spend on goods and services.

Note that this presumes a functioning market (free or otherwise). The company store knows it is the only game in town, so it doesn't have to appeal to anyone.


Markets have a bid and an ask.

If you have robust supply and real competition, the ask should trend towards cost plus some profit, not whatever maximum price people will pay out of desperation.


what does robust supply and real competition look like when everyone gets a million a year? If everyone makes a million a year, you need a lot more than what we pay today to convince people to come into work. If you want to sell a burger, you have to sell it at a profit. Ergo, you must pay more for a burger if everyone makes a million a year. You have to convince the whole supply chain to keep working. The only way we know how to do that at scale, outside of force, is money.

Now the burger cost goes up, and working people have even more money than "normie" millionaires. I imagine people are going to be more free with their money, so they pay more for the burger. And this will settle, per the law of supply and demand.

That part is obvious.

What is not clear to me is how the new price would work out. Maybe it would work out to pretty much the same relative cost it is today, but in inflated dollars. And the rest of the market is doing the same thing. And landlords know you have the money. The squeeze comes back. Cue Econ 101/102.


This discussion sort of involves magic AI doing a lot of the work. That should be cheap.

Tight control of scarce resources is certainly something that would still be an issue. Hopefully we find ways to solve it with politics instead of violence.


I think you're right, and when we talk about UBI it should be expressed in what it can provide not some arbitrary number. Can it provide all required needs (housing, food, transport, entertainment, etc) or not?


I think of it as closer to $500/month, with supply-side government subsidies of food and housing, and then increasing taxes such that the mean person nets 0$.


Not necessarily. The government controls prices, the government assigns _everyone_ some work no matter how meaningless it is; so instead of one street sweeper we would get 10. Everybody is paid just enough to live and have work assigned to not slack (I don't believe in utopia where money is paid for doing nothing because this utopia sounds extremely dystopian). I know just a place where people lived like that for 40-something years - Soviet Union! It wasn't terrible for majority, it wasn't great either. Also, it didn't last that long because it was unsustainable.

Our AI overlords think that they will be able to just prompt their LLMs to optimize this regime and make it last but their stupid LLMs can't yet figure out whether to take a car to the carwash or to go by foot, so they are not even close to that.

What's bad for us is that they are now wealthy enough to keep dragging us into this dystopia for a while until something changes.


Only if the government funds it by printing money. If it's funded with taxes on the rich there's no reason for any inflation.


Looks a lot like Swift! Awesome!


There are literally 1000s of these types of apps. Why is this on the Front Page?


1000s?

I'd love to know a few more local LLM apps that are available on Android and iOS and Mac/PC under the same branding that I can point my non-technical friends to as a ChatGPT alternative that works offline (but still has sync across the devices).

Could you recommend a few?


StumbleUpon?


Personally my favorite spiritual successor to stumbleupon has been cloudhiker.net. I found kagis to be too personal blog focused for my tastes. I love that kagi is doing so much of this out in the open though.

There are a surprising amount out there: https://blog.woblick.dev/en/2025/best-stumbleupon-alternativ...


Hi, creator of Cloudhiker here. Thanks for mentioning my site! Let me know if you have any questions, issues or ideas.


There are still a lot of alternatives:

http://cloudhiker.net

https://www.offscopes.com

Newsletter version if you prefer: https://randomdailyurls.com


I miss StumbleUpon so much!


First thing I thought... honestly we should bring it back anyway


Can anyone get LinkedIn>English working? Nothing I've found and pasted in has seemed to work... just spits back out the original


Maybe that's the same problem as translating CEO memos to English. A large body of text, with no content, or at least very little.

So far I've been hesitant to put memos from our CEO into an LLM for a summary, I fear that it will just spit out "Nothing to concern yourself with" every time.


For those unaware, Claude Code comes with a built in /insights command...


insights is straight ego fluffing - it just tells you how brilliant you are and the only actionable insights are the ones hardcoded into the skill that appear for everyone. things like be very specific with the success criteria ahead of time (more than any human could ever possibly be), tell the llm exactly what steps to follow to the letter (instead of doing those steps yourself), use more skills (here's an example you can copy paste that has 2 lines and just tells it to be careful), and a couple of actually neat ideas (like having it use playwright to test changes visually after a UI change)


It gave you a couple neat ideas and you're complaining.


Some people just can't take a compliment, especially if it's generated. (I'm one of them.) Still, /insight did give useful help, but I wasn't able to target it to specific repo/sessions.


Isn't it using the sessions in the cwd where you're running it?


Ohh this is exciting, I kinda overlooked it. I assume there are still a lot of differences, especially for accross teams. But I immediately ran it, when I saw your comment. Actually still running.


true, the best comes out of it when one uses claude code and codex as a tag team


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: