71–80 of 471 posts
Everything is "fast, cheap, good--pick two." This is no different.
I like the analogy but which 2 is AI coding? Fast & Cheap (but not Good?) - I wouldn't really say that AI coding is "cheap" Cheap & Good (but not Fast) - Again, not really "cheap" Fast & Good (but not Cheap) - This seems like maybe where we're at? Is this a bad place?
It is and will always be about: 1) properly defining the spec 2) ensuring the implementation satisfies said spec
Which with the advent of LLMs just lowered our standards so we can claim success.
Sometimes I can get away with 3K LoC PRs, sometimes I take a really long time on a +80 -25 change. You have to be intellectually honest with yourself about where to spend your time.
Defining “Gambling” like isn’t really helpful.
Fascinating how HN is torn about vibe coding still. Everybody pretty much agrees that it works for some use cases, yet there is a flamewar (I mean, cultured, HN-type one) every time. People seem to be more comfortable in a binary mindset.
Assigning work to an intern is gambling: they're inherently non-deterministic and it's a roll of the dice whether the work they do will be good enough or you'll have to give them feedback in order to get to what you need.
That’s very true. But interns aren’t supposed to be doing useful work. The purpose of interns is training interns and identifying people who might become useful at a later date. I’ve never worked anywhere where the interns had net productivity on average.
It is and will always be about: 1) properly defining the spec 2) ensuring the implementation satisfies said spec
But even accounting for all these "hard" constraints and metrics, there are clearly reasons to prefer some possible programs over others even when they all satisfy the same constraints and perform equally on all relevant metrics.
We do treat programs as efficient causes[1] of side effects in computing systems: a file is written, a block of memory is updated, etc. and the program is the cause of this.
But we also treat them as statements of a theory of the problem being solved[2]. And this latter treatment is often more important socially and economically. It is irrational to be indifferent to the theory of the problem the program expresses.
When I have Claude create something from scratch, it all appears very competent, even impressive, and it usually will build/function successfully…on the surface. I have noticed on several occasions that Claude has effectively coded the aesthetics of what I want, but left the substance out. A feature will appear to have been implemented exactly as I asked, but when I dig into the details, it’s a lot of very brittle logic that will almost certainly become a problem in future.
This is why I refuse to release anything it makes for me. I know that it’s not good enough, that I won’t be able to properly maintain it, and that such a product would likely harm my reputation, sooner or later. What frightens me is there are a LOT of people who either don’t know enough to recognize this, or who simply don’t care and are looking for a quick buck. It’s already getting significantly more difficult to search for software projects without getting miles of slop. I don’t know how this will ultimately shake out, but if it’s this bad at the thing it’s supposedly good at, I can only imagine the kinds of military applications being leveraged right now…
Overall I’m a fan, but yes there are things to watch for. It doesn’t replace skilled humans but it does help skilled humans work faster if used right.
The labor replacement story is bullshit mostly, but that doesn’t mean it’s all bad.