But what's the point of re-building "standard software" if it is so standard that it already exists 100 times in the training data with slight variations?
I read this attitude very often on HN. "If someone else has already built it before, your effort is a waste of time." To me, it has this "Someone else already makes money from it, go somewhere else where you dont have competition." Well, I get the drift... But... Not everyone is into getting rich. You know, some of us just have fun building things and learning while doing so. It really doesn't matter if the path has been walked before. Not everything has to be plain novelty to count.
Very cool book. I think a reason why ML has seen so much progress despite benchmark overfitting/abuse is that results are "regularized" by real world applications and the Lindy effect. Methods, or research, that abuse benchmarks aren't adopted by follow-up research so they tend not to survive. And they aren't adopted because people try them but then find out that they don't generalize to other/newer benchmarks. So the system works not because of specific benchmarks, but because of how the community as a whole deals with benchmarks.
Looking for 5 seconds at the github profile I see a bunch of music-related stuff, and also a bunch of contributions to private repos that we have no idea what they are. I get the productivity guru anti-pattern, but I honestly don't know what you're looking at that merits this kind of reflexive personal attack.
Competitiveness doesn't really come from architecture, but from scale, data, and fine-tuning data. There has been little innovation in architecture over the last few years, and most innovations are for the purpose of making it more efficient to run training or inference (fit in more data), not "fundamentally smarter"
A bit off-topic, but it's interesting how the first thing I check now is whether this is a vibe coded app (which it seems to be) or something that had serious effort put into it.
I mean, "effort" to me in this context is what the creator of $project thinks it is worth their time. Don't you agree? If you want to learn a new computer language yourself, vibecoding will probably not help you. If you want to create something to scratch your itch, and spend time and mental effort in getting it polished, isn't that effort? It is not automatic, even with vibecoding, getting out a good app/site that solves a need in an elegant, functional manner for the user.
I think your last point is the important one. I don't mind vibe coded app if they are polished. But a polished vibe coded app looks like a non-vibe-coded app because of the polishing. The polishing is 95% of the effort. This app here looks fully vibe coded, without much polishing, at least to me.
> It is not automatic, even with vibecoding, getting out a good app/site that solves a need in an elegant, functional manner for the user.
This feels like a vibecoded comment.
To address the "substance" of your "comment": yes, creating a polished product requires effort, but this is not a polished product: as pointed out by numerous commenters, it provides nothing new, and what it does provide is broken. Thus the GP's comment that it is vibecoded slop and not worth taking seriously.
My rhetorical question was broader, because GP comment was a generic one, not specific to this project.
I would ask you to be more mindful in your replies.
It doesn't matter, the answer is the same. Using vibecoding is less effort that not using it, so of late we see a lot of low-effort vibecoding projects, of which this is one. Ergo, vibecoding is an easily-spotted red flag for projects that are not worth taking seriously.
> I would ask you to be more mindful in your replies.
You should take your own advice. Also, don't be a dick.
> It doesn't matter, the answer is the same. Using vibecoding is less effort that not using it, so of late we see a lot of low-effort vibecoding projects, of which this is one. Ergo, vibecoding is an easily-spotted red flag for projects that are not worth taking seriously.
And the whole point of my initial reply was to question the definition of "effort".
> You should take your own advice. Also, don't be a dick.
I think your reply perfectly illustrates the situation.
Not a fruitful discussion anyway, enjoy clicking down arrows.
You're offering a product, not a vibe project, so I disagree.
If vibe coding would lower cost while maintaining quality then this would be a fair argument, but the reality is that its a lazy way and frankly it's not programming.
GP was speaking of the first thing they now check on every new project they find is whether it's vibecoded or there is actual "effort" in it. Hence my comment.
reply