Thanks, means a lot. As the author of one such article (that might have been the catalyst even), I'm guilty of this myself, and as I dove deeper into understanding what Cursor actually built, and what they think was the "success", the less sense everything made to me.
That's why taking a step back and seeing what's actually hard in the process and bad with the output, felt like it made more sense to chase after, rather than anything else.
I'm glad I could take people on a journey that first highlighted what absolutely sucks, to presenting something that seemingly people get pleasantly surprised by! Can't ask for more really :)
What is interesting is that yours is the first example of what this tech can do that resonates with me, the things I've seen posted so far do not pass the test for excitement, it's just slop and it tries to impress by being a large amount of slop. I've done some local experiments but the results were underwhelming (to put it mildly) even for tiny problems.
The next challenge I think would be to prove that no reference implementation code leaked into the produced code. And finally, this being the work product of an AI process you can't claim copyright, but someone else could claim infringement so beware of that little loophole.
Knowing you browse HN quite a lot (not that I'm not guilty of that too), that's some high praise! Thank you :)
I think the focus with LLM-assisted coding for me has been just that, assisted coding, not trying to replace whole people. It's still me and my ideas driving (and my "Good Taste", explained here: https://emsh.cat/good-taste/), the LLM do all the things I find more boring.
> prove that no reference implementation code leaked into the produced code
Hmm, yeah, I'm not 100% sure how to approach this, open to ideas. Basic comparing text feels like it'd be too dumb, using an LLM for it might work, letting it reference other codebase perhaps. Honestly, don't know how I'd do that.
> And finally, this being the work product of an AI process you can't claim copyright, but someone else could claim infringement so beware of that little loophole.
Good point to be aware of, and I guess I by instinct didn't actually add any license to this project. I thought of adding MIT as I usually do, but I didn't actually make any of this so ended up not assigning any license. Worst case scenario, I guess most jurisdictions would deem either no copyright or that I (implicitly) hold copyright. Guess we'll take that if we get there :)
This is not legal advice, but I think one should always add a license, not so much for copyrights but for the "no warranty" part. If someone claims copyright once can add whatever license was used in the original work.
In general where I live (Spain), main baseline is fault/negligence, so basically "whoever causes damage by fault or negligence must repair it". They'd need to be able to attribute the fault/negligence to me, which since this is just public code with me promising nothing, will be really hard for them to "prove".
The license implicitly defaults to "I own all the rights", so no one is able to override that implicit license by copying the code and slapping their own license on top, I'm not sure if this is what you were thinking about when you said "claims copyright once can add whatever"?
Then on a different note, I'm not licensing/selling/providing any terms, so it's short of impossible for someone to credibly claim I warranted anything, there are no terms in the first place, except any implicit ones.
Maybe in the US works differently, and because Microsoft is in the US, that can somehow matter for me. But I'm not too worried about it :)
Thanks for the consideration and care though, that's always appreciated! :)
That's why taking a step back and seeing what's actually hard in the process and bad with the output, felt like it made more sense to chase after, rather than anything else.