Surely that’s not all it takes?

A steady diet of watching nothing but fox news has a similar effect

I took the trouble of logging in to HN to call bullshit on this whole thread. The reason these teenagers aren’t building standalone apps is generally because they know that web apps are the future. Moreover, there are dozens of new travel planning startups every year (YC regularly funds them!) and they seem to discover the same thing that Microsoft did—the real reason they stopped updating this magical app—which is that everybody wants better travel apps but nobody wants to pay for it.

I’m sure someone will crack the code someday and I’m glad they will keep trying, but I refuse to accept the premise that $100 Apple developer accounts are their primary impediment.

$100 is $100, you seem to comment from a position of privilege. When I learned programming, in my early 20s, that was close to my monthly salary. Granted I've been a paid programmer for more than 15 years now and I make more than that, but, even so, seeing as app development is not what brings me money it looks like a waste to me to throw $100 at something each year so that I'd have the privilege of running my code on a piece of hardware I already own.

And let's say that maybe I'm a cheap bastard, but the reality remains that $100 is still a lot of money for a lot of young people around the world who have just gotten into programming.

No way my parents would have forked over $100 to me on some computer thing they didn't understand. Being able to spend your parents money on the internet as a kid is rare.

You know who else said web apps are the future? Steve Jobs when he launched the iPhone.

Maybe web apps are going to be used for commercial things but nothing beats the power of being able to write your own tools, and its just so easy to do that locally as its always been. A little bash script or some python goes far.

This year I launched https://www.tabbydata.com, on track to make $500/month by February.

That's almost FSWEP money :-)

Shoot me an email if you’d like—I’d be happy to share any learnings from what I built if relevant.

For other public BigQuery datasets I’d certainly consider just adding them to the demo for free—which specific Bitcoin/finance datasets did you have in mind?

For private datasets, we’re looking at adding that functionality to the core Tabby service (that’s the SaaS this relates to). Please email for info!

Are you looking to set it up for another public dataset or your own private one? Either way, shoot me an email (on the demo page and also in my HN profile) and I’ll see what I can do.

Thanks for noting this! The functionality is definitely not perfect, and the opaque nature of the underlying model does not give much opportunity for tweaking. I suspect slightly altering your input might help drive better output.

Really? Wow, I would not have expected that to work. Might be one advantage of using this general model instead of a more specialized one.

The weather dataset has a bit of an unorthodox schema IMO, which gives the model more trouble than usual. That’s kind of the point of this demo, though: to what extent is generated SQL like this useful—despite its flaws—in the context of real-world datasets? Jury is still out :)

Nice! Yeah I have no doubt that a specialized model could beat this general one, although I find the output from the general one to be uncanny at times. Would love to hear your expert opinion on how they compare!