their product attempts to duplicate your local dev setup on a machine on the cloud, which means they copy your .env / local postgres db, local docker-compose stack etc. It worked quite well for me, I tried it just now (except for postgres + setting up git). I think the product is quite good but still needs a bit of polishing.

I'm a bit frustrated that they restrained EU users from downloading their app, but I guess they just want to avoid dealing with GDPR, which is fair for an early startup!

Oof, I don't think we paid super close attention to the country list when shipping our app. We'll fix this for you, but it might be a few days for things to make it out of review. Really appreciate you trying it out. It's still pretty early so things are still rough around the edges, but we'll be keeping an eye out on our logs for bugs, and feel free to reach out to feedback at boxes.dev if you notice any issues.

Youtube revanced on your phone + ublock on firefox and you'll never see youtube ads again. There's also a replacement app for android TV that I forgot the name of that works well. Do not use chrome, google nerfed its ad-blocking capabilities a while ago

I see this kind of first-gen coding agents a bit like the AI-era microsoft excel: you need to be a poweruser to use it correctly, otherwise you'll end up failing catastrophically. Hence the amount of different ways to use it.

Having an "unfinished" product is also a great marketing tool for companies like anthropic: each skill/plugin/guide that you see on the internet is boosting their SEO + social validation metrics.

There is also a significant amount of accounting fraud happening right now, according to Michael Burry: https://x.com/michaeljburry/status/1987918650104283372?lang=...

The comments to his tweet, if true, tend to say that the real lifespan of an AI chip tends to be around 1 to 3 years in reality, since racks don't cool down that well. Not sure if these commenters are a reliable source though lol. https://x.com/xdire_me/status/1987920424978837711

In france, there was an edition of the discworld series literally called "pocket", and yes it sometimes fit in pockets (which had to be on the bigger end of pockets though), especially if you bended the book a little. Looked like this: https://www.babelio.com/livres/Pratchett-Les-annales-du-Disq...

The first books of the discworld were thin too.

Thanks, I didn't know that! Definitely smaller than the paperbacks we had in the UK, and pocket-sized.

I apologize for making you sad, seeing all the comments made me realize that I should have been way less aggressive with the AI proofreading ; I wanted the sentences to feel a bit more Terry Pratchetty and thought a lot of Claude's suggestions were really better than what I had made. I actually agree to your point too

I write science fiction as a hobby and am in writing critique groups. One of the first rules of critiquing writing is not to suggest how to say things, but only to say what a certain phrase made you feel (confusion, boredom, etc).

LLMs harnesses try to make them useful to suggest things, but this is the most destructive thing you can do to a writer. You can work around it by just feeding Claude a writing critique skill.

You should have done it by hand man. It would have been so much more <3 <3 <3

And Terry Pratchett would have loved it too. Even if it were clumsy.

But thanks for being kind in taking criticism.

> way less aggressive with the AI proofreading

It’s funny how anytime an article gets called out for being AI slop on HN, the author’s reaction is something like that: “oh yeah sorry I used AI but just for proofreading I swear, I should’ve done just a tiny bit less”.

No one seems to get the message that relying on AI at all is what makes writing shit. Good writers have confidence in what they produce. The fact that you’re willing to incorporate any AI suggestion at all means you’ve already lost the battle.

I'm not a writer but I do write quite a bit for scientific reasons. I'd like to add a small tweak to your comment.

The people I know have no confidence whatsoever in their writing, rewriting and rephrasing the same paragraph over and over until they either run out of time or give up. They also circulate their drafts among colleagues and ask for their opinions too.

It's not the confidence what makes good writing, but rather putting in the work.

At least in technical writing if your English is not too good you can replace some of it with math formulae and get away with it. Ish.

Tbh my first couple research papers were brutally savaged by reviewers until I spoke to a lady at my university's Academic English department. In fact I was sent there by an internal reviewer who refused to pass my early-stage report otherwise. The lady at the Academic English dept pointed out one thing I was doing and it immediately clicked and I've only got good words about my writing style since.

Know what that One Simple Hack was? I spent my youth writing Sci-Fi, Fantasy and Horror as a hobby. So naturally when it came to writing papers, I thought, hey, I know how to write. It's like literature.

Shockingly, it is not. Like, at all! In literary writing it's basically sacrilege to write the same thing in the same words twice. In technical writing that is what you must do. Unless you want to confuse everyone about what you mean. So I was trying to make my technical writing "not boring" by not repeating the same expressions and instead finding new, creative ways to refer to the same concepts in different places, and that just made reviewers really angry because they never knew what I meant. I stopped doing that -and also generally tightened up my use of terminology- and that was it. Now every paper gets at least one reviewer that says "this is a well-written paper".

Then they brutally maul me anyway on all the rest, of course but, eh, what can you do :D

P.S. Dunno, maybe "that's a well-written paper" is what everyone says when they're looking for something nice to say before they let rip. I sometimes do it too. People do that all the time, don't they? I had calcific tenonditis and I went to a doctor and he told me "you are really brave, others in your condition would be screaming their heads off" (from the pain). And I remembered that my father had the same thing when I was a kid and he'd gone to a doctor and come back bragging that the doctor told him he was so brave, others would be screaming their heads off. I wish people didn't do that, I'm fine being just like everyone else, honest. Just don't make me doubt my mediocrity, you know?

I’m reasonably sure that one can use AI as a fancy spellcheck plus grammar check — this of it as a copy editor, not a co-author. Even professional authors have beta readers and copy editors.

Yeah this was the way I originally started to read his books. The translations were amazing. When I later started to read the originals, I was surprised at how difficult it was for me to understand: the jokes are really designed for native speakers in a lot of ways, and the vocabulary isn't that simple

It's true that AI is making traditional algorithmic abilities matter less in the job market, so people naturally are less drawn to it. Just look at the stackoverflow demise story: SO is also a community for people who like solving coding issues, and they are experiencing a really steep decline in traffic.

But I think the other, maybe even more significant issue is that the market for coding-related tools and services is completely oversaturated these days. I recently saw that the daily launches on producthunt increased 20 fold due to AI. The market for pure software stuff is extremely competitive nowadays.

Really nice simulation! This reminded me of a youtuber that studied chart analysis (in the sense of analyzing financial charts to try to play on the stock market), and through simulations realized that markov processes reproduce roughly the patterns that people usually use in this field ("resistance", etc.)

Not sure if it was a typo or not but "colleagues" is a great word, I'm going to start using it.