> Recently I was listening to music and doing some late night vibe coding when I had an idea. I love art and music, but unfortunately have no artistic talent whatsoever. So I wondered, maybe Claude Code does?

Do I need to read further? Seriously, everyone has talent. If you're not reaady to create things, just don't do it at all. Claude will not help you here. Be prepared to spend >400 hrs on just fiddling around, and be prepared to fail a lot. There is no shortcut.

Author of the article here. Appreciate your sentiment here, but my goal wasn’t trying to make a hit song or shortcut the obvious very significant time and effort that goes into creating any sort of art. It was meant as a fun experiment to try to highlight a feeling that we’re barely scratching the surface of the breadth of things that agentic coding may be able to tackle. I’ve been learning guitar and taking painting classes in my free time, but it’s not my profession nor something I was encouraged to do when I was young. Thanks for the comment, it’s helpful to see ways I can improve my writing style

I've gotta come to OPs defense here. In the age of Suno indistinguishable-from-human-quality hits, this whole endeavor was an art piece and more interesting than most human OR AI music I've heard in the past year.

The medium was using the "wrong" tool for the job, which creative musicians do on a regular basis. And the output was so cool, it really felt like a relic from a different era even though it's hyper-modern.

Yeah, it's just weird to expect people to find AI-generated art interesting when the person generating it has no unique take or talent. This is the worst case where there is absolutely 0 creativity in the process and the created "art" reflects that imo.

I don't find it interesting in an artistic way, but I do find it very interesting from an "AI experiment" angle.

I don't get what the "AI experiment" angle here is? The fact that AI can write python code that makes sounds? And if the end product isn't interesting or artistically worthwhile, what is the point?

> What's the point if human-made art isn't interesting or artistically worthwhile?

Because it is a human making it, expressing something is always worthwhile to the individual on a personal level. Even if its not "artisticallly worthwhile", the process is rewarding to the participant at the very least. Which is why a lot of people just find enjoyment in creating art even if its not commercially succesful.

But in this case, the criteria changes for the final product (the music being produced). It is not artistically worthwhile to anyone, not even the creator.

So no, a person with no talent (self claim) using an LLM to create art is much less worthwhile than a human being with no/any talent creating art on their own at all times by default.

Comparing this to penpot, which is free as long as you self-host.

Not sure why I would pick this over a self-hostable battle-tested option.

You can get arrested for this in my country, fun fact.

I guess that's how you prevent anything, just make it illegal and the exploit becomes an unintended illegal feature, like occupying the low-freq radio signal.

Follow up question (Not OP), would alphafold more be used to experiment with an already-defined theory that you have, or could you also make some toy projects (e.g. how people make projects around trading engines).

I'm wondering if I could find a fun weekend project in alphafold just to see what it's like.

> A few years ago I submitted a full TypeScript rewrite of a text editor because I thought it would be fun. I hope the maintainers didn't read it. Sorry.

Love the transparency. To be fair, rewrites are almost impossible to review. Anything >5k diff takes at least multiple review cycles. I don't know how some maintainers do it while also working on the codebase themselves

4.1 or 4.5? I did not need to steer Opus 4.5 at many points. A good description was more than enough

Most of the time there's an archive.is link in the comments

Unfortunately archive articles don't work for the worst offenders: Wall Street Journal, Financial Times (FT) and Bloomberg most notably. Paywalled sites should be automagically highted in RED when posted in HN, by HN script.

Archive links work for some percentage of WSJ, FT and Bloomberg. And for the ones that don't work, if you wait a while (few hours to a day or two) and try again, many of the ones that did not work begin to work after the delay. Whether the article will still be valuable to read a day or two later depends upon the content.

  Location: Delft, Netherlands NL
  Remote: Yes
  Willing to relocate: Yes
  Technologies: Rust, TypeScript/JavaScript, Golang, Ruby
  Résumé/CV: ramones (dot) dev (slash) hire-me
  Email: ramonvansprundel (ta) gmail (tod) com

I have 3+ Years of Experience as a SWE. I mostly worked with a TypeScript stack for work building Shopify platinum apps, and I've made and contributed to dozens of Rust projects (sudo-rs, nptd-rs, zed, uutils, firefox).

I'm also open to exploring new fields. I don't work well in an assembly line ticket processing setup, as this does not excite me in any way. I love diving deep into topics like memory management, architecture, solutioning and all that jazz!

I'm also available as extra man-power for cool (F)OSS projects I can help out with

Should we also take away their television? Do comic books make people dumb too?

I get the argument, but it's just not a solution

Yes it is. The internet is something you should sit down to use. Adults or children should not be followed by it everywhere they go.

Ok grandpa

To be fair, the projects goal is to write code.

That said, it appears to be not very maintainable code.