Hell, I use the (closed-source) app Smart Audiobook Player and I wanted Audiobookshelf integration. I asked Claude, it decompiled the app, added the extra code, recompiled the APK and it works perfectly, syncing my book's progress with the server.

Truly magical, it would have taken me months.

That’s super cool.

If no post planned, please consider - that’s very “an app is a home cooked meal”, and I love it.

I could write something, but it would be "I told Claude to do this and it did, I'm happy", there isn't really much more detail to write about. What would you like to see?

I’ve seen a few posts just like that ^_^

It’s mostly your original story of motivation, in brief prose, that does the heavy lifting of a satisfying post,

followed by exactly what spec and names of tools you used, mundane as they may feel,

your exact prompt(s) (because this is of technical interest in and of itself),

and screenshots of excerpts/link to output.

Things that stood out to you along the way would also stand out to others.

The comment alone will probably be the most intriguing one I read all day.

Huh, sure, I'll write something up today! You can subscribe to https://stavros.io to get an email (there's a form under each article).

Maybe they mean you can be not employed and build products yourself? Technically true, but that's like running your own surgeries or something, you're still doing surgery.

Yeah, memorization is very underrated.

Memorization increases the size of the building blocks you can use.

Mathematics is where I see this most clearly. Why memorize hundreds of theorems? Because then you can just cite them on the fly when doing real mathematics. If you had to re-derive everything, you'd be stuck doing undergrad level math forever.

I never memorized the trig identities, but used them so much I knew them anyway.

so you memorized them, you just didn't explicitly do it.

Memorizing is an active activity. Simply remembering something you use frequently is not the same.

I write because I just find it hard to form long, coherent thoughts without writing.

When trying to think on the fly, I often say something jumbled and nonsensical, then make another attempt after thinking for a second.

I need that editing step to even get my paragraphs or long sentences just right.

But why am I writing this comment? I don't know.

I'm not American or in America, but I wouldn't use a work laptop for anything personal.

I mean I have my own laptop and phone, why would I use a work device for that stuff?

> I mean I have my own laptop and phone, why would I use a work device for that stuff?

Because you're traveling for work, and carrying two separate laptops eats into your limited baggage size/weight. Things are marginally better now that everything uses the same standard charger, but not much.

Somehow despite travelling a lot for work, I've never had this happen.

I just do personal stuff on my phone.

Lucely absolutely does not catch the hard c. Surely there is no word in the English language where "ce" has a hard c, only loanwords like celt.

I'm interested in how one would prove that one way or another.

It seems to me that in the past there probably was lots of shoddy workmanship and just no-one paid attention to it.

But I have no proof of that.

Fortunately, there are millions of buildings that remain standing as evidence of what was done in the past. So at least there's that!

Buildings don't get taken down because 'they were built poorly', it's cheaper to rebuild than refurbish.

And we can accommodate for 'selection bias'.

We have all of the historical evidence we could ever want for 'how things were built', basically 'infinity examples'.

I think some things were more robust, particularly some of the old framing, like in Europe, with non load-bearing walls etc. Those will stand for 1K years, but arguably unnecessary.

Massive selection bias - only the good quality ones remain standing, the low quality ones are not.

You have to get a representative sample, that's the tricky part.

So there's that!

As long as it doesn't cost me anything, I'd like to see it play out in court and know for sure.

But that is very unlikely even if everyone adopted it, which they won't.

I mean you might as well write "any competing project will be considered infringement". It doesn't cost you anything either.

People were still gaming GitHub profiles before AI, sometimes even just reuploading existing repos as their own.

I think the classic one is pedophiles and protecting children.

If someone uses ChatGPT to create child porn or worse, to get help tracking down and meeting children, there is NO way in hell the public will accept "don't punish the toolmaker" as a principle.