I've already experienced being handed a vibe coded app, which so far it's been a communication problem/code cleanliness eg. don't leave two versions of an app and not say which one is active. And the docs man so many docs/redundant/conflicting.
Where's the shovelware? Why AI coding claims don't add up
51–60 of 498 posts
Re: Where's the shovelware? Why AI coding claims don't add up
#52This tracks with my own experience as well. I’ve found it useful in some trivial ways (eg: small refactors, type definition from a schema, etc.) but so far tasks more than that it misses things and requires rework, etc. The future may make me eat my words though. On the other hand, I’ve lately seen it misused by less experienced engineers trying to implement bigger features who eagerly accept all it churns out as “go…
> implements some logic from scratch where there certainly is more than one suitable library, making this code we now own - is some behemoth of a PR trying to do all the things Depending on the amount of code, I see this only as positive? Too often people pull huge libraries for 50 lines of code.
Yes, for leftpad-like libraries it's fine, but does your URL or email validation function really handle all valid and invalid cases correctly now and into the future, for example?
Re: Where's the shovelware? Why AI coding claims don't add up
#53Hmm, I definitely have more issues with AI generated code that I wouldn’t have if I did it all manually, but the lack of typing may make up for the lost time itself.
Re: Where's the shovelware? Why AI coding claims don't add up
#54Earlier quoted context omitted.
Same. On many days 90% of my code output by lines is Claude generated and things that took me a day now take well under an hour. Also, a good chunk of my personal OSS projects are AI assisted. You probably can't tell from looking at them, because I have strict style guides that suppress the "AI style", and I don't really talk about how I use AI in the READMEs. Do you also expect I mention that I used Intellisense and…
The author’s main point is that there hasn’t been an uptick in total code shipped, as you would expect if people are 10x-ing their productivity. Whether folks admit to using AI in their workflow is irrelevant.
I don’t think this is necessarily true. People that didn’t ship before still don’t ship. My ‘unshipped projects’ backlog is still nearly as large. It’s just got three new entries in the past two months instead of one.
Re: Where's the shovelware? Why AI coding claims don't add up
#55This makes some sense. We have CEOs saying they're not hiring developers because AI makes their existing ones 10X more productive. If that productivity enhancement was real, wouldn't they be trying to hire all the developers? If you're getting 10X the productivity for the same investment, wouldn't you pour cash into that engine like crazy? Perhaps these graphs show that management is indeed so finely tuned that they'…
A lot of these C-suite people also expect the remaining ones to be replaced by AI. They subscribe to the hockey-stick "AGI is around the corner" narrative.
I don't, but at least it is somewhat logical. If you truly believe that, you wouldn't necessarily want to hire more developers.
Re: Where's the shovelware? Why AI coding claims don't add up
#56Multiple things can be true at the same time: 1. LLMs do not increase general developer productivity by 10x across the board for general purpose tasks selected at random. 2. LLMs dramatically increases productivity for a limited subset of tasks 3. LLMs can be automated to do busy work and although they may take longer in terms of clock time than a human, the work is effectively done in the background. LLMs can get me…
> Setting up a scaffolding for a new website? LLMs are amazing at it.
So amazing that every single stat showed by the author in the article has been flat at best, despite all being based on new development rather than work on existing code-bases.
Re: Where's the shovelware? Why AI coding claims don't add up
#57What the author is missing is the metric that matters more than shipping product: how much happier am I when my AI auto complete saves me typing and figures out what I'm trying to articulate for me. If devs using copilot are happier--and I am, at least--then that's value right there.
Re: Where's the shovelware? Why AI coding claims don't add up
#58Earlier quoted context omitted.
> implements some logic from scratch where there certainly is more than one suitable library, making this code we now own - is some behemoth of a PR trying to do all the things Depending on the amount of code, I see this only as positive? Too often people pull huge libraries for 50 lines of code.
I'm not talking about generating a few lines instead of importing left-pad. In recent PRs I've had: - Implementing a scheduler from scratch (hundreds of lines), when there are many many libraries for this in Go. - Implementing some complex configuration store that is safe for concurrent access , using generics, reflection, and a whole other host of stuff (additionally hundreds of lines plus more for tests). While I c…
Someone vibe coded a PR on my team where there were hundreds of lines doing complex validation of an uploaded CSV file (which we only expected to have two columns) instead of just relying on Ruby's built-in CSV library (i.e. `CSV.parse` would have done everything the AI produced)
Re: Where's the shovelware? Why AI coding claims don't add up
#59This makes some sense. We have CEOs saying they're not hiring developers because AI makes their existing ones 10X more productive. If that productivity enhancement was real, wouldn't they be trying to hire all the developers? If you're getting 10X the productivity for the same investment, wouldn't you pour cash into that engine like crazy? Perhaps these graphs show that management is indeed so finely tuned that they'…
Today you will learn what diminishing returns are :) You can only utilize so many people or so much action within a business or idea. Essentially it's throwing more stupid at a problem. The reason there are so many layoffs is because of AI creating efficiency. The thing that people don't realize is it's not that one AI robot or GPU is going to replace one human at a one to one ratio. It's going to replace the amount…
I disagree that layoffs are because of AI-mediated productivity improvements.
The layoffs are primarily due to over-hiring during the pandemic and even earlier during the zero-interest-rate period.
AI is used as a convenient excuse to execute layoffs without appearing in a bad position to the eyes of investors. Whether any code is actually generated by AI or not is irrelevant (and since it’s hard to tell either way, nobody will be able to prove anything and the narrative will keep being adjusted as necessary).
Re: Where's the shovelware? Why AI coding claims don't add up
#60Multiple things can be true at the same time: 1. LLMs do not increase general developer productivity by 10x across the board for general purpose tasks selected at random. 2. LLMs dramatically increases productivity for a limited subset of tasks 3. LLMs can be automated to do busy work and although they may take longer in terms of clock time than a human, the work is effectively done in the background. LLMs can get me…
If it can figure out where dependencies come from I'm going to have to look more into this. I really hate the way injection makes other people's code bases impenetrable. "The framework scans billions of lines of code to find the implementation, and so can you!"