281–290 of 299 posts
Before that you were crying about the singularity and how we're super close it and in 6 months AI will be basically Einstein. Nothing has given me more joy than to see this AI slop fail.
Here's a 100 page document generated with AI and the other person will shrink it with AI at the end of the day those 2 lines of cognitive effort would've been a better deal than sending slop back and forth.
Earlier quoted context omitted.
So, if I understand correctly, you've seen plenty of people that didn't do what he did? This was not a compelling argument.
> you've seen plenty of people that didn't do what he did? Yes, because I've seen them build software that was actually used. And I've seen a few that did just like him, impressive sounding projects that had no usage. I understand it's something subjective. I get the same feeling when looking at Damien Hirst's monstrouly expensive stuff that leaves me cold. Even after I get the concepts behind the works, my end feeli…
That METR study gets a lot of traction for its headline; and I doubt many people read the whole thing—it was long—but the data showed a 50% speed up for the one dev with the most experience with Cursor/AI, suggesting a learning curve and also wild statistical variation on a small sample set. An errata later suggested another dev who did not have a speedup had not represented their experience correctly, but still stro…
It was such a great study imo and rightfully deserves a lot of attention since it's a great alternative to twitter vibes. But to stop here and say AI coding doesn't work will just not hold up well. We have a sample size of 16 developers for 250 tasks. Here is my data point: adding AI to your engineering team really is like adding a new member. At first it slows everybody down: explain this, explain that, stupid mista…
The person who showed a speed-up indicated over a week of prior experience with cursor while all others under a week.
So I have all kinds of problems with this post. First, the assertion that the best model of "AI coding" is that it is a compiler. Compilers deterministically map a formal language to another under a spec. LLM coding tools are search-based program synthesizers that retrieve, generate, and iteratively edit code under constraints (tests/types/linters/CI). That’s why they can fix issues end-to-end on real repos (e.g., SW…
The problem of course is when people throw away the prompt and keep the code, like the code is somehow valuable. This would be like everyone checking in their binaries and throwing away their source code every time, while arguments rage on HN about whether compilers are useful. (Meanwhile, compiler vendors compete on their ability to disassemble and alter binaries in response to partial code snippets.)
The right way to do AI programming is: English defines the program, generated code is exactly as valuable as compiler output is, i.e. it's the actual artifact that does the thing, so in one sense it's the whole point, but iterating on it or studying it in detail is a waste of time, except occasionally when debugging. It's going to take a while, but eventually this will be the only way anybody writes code. (Note: I may be biased, as I've built an AI programming tool.)
If you can explain what needs to be done to a junior programmer in less time than it takes to do it yourself, you can benefit from AI. But, it does require totally rethinking the programming workflow and tooling.
Earlier quoted context omitted.
what is the cost of enabling someone to create little pieces of software if he otherwise wouldn't? I'm no advocate of vibe coding serious commercial software, but to do little DIY stuff - absolutely.
No one is forbidding people creating little pieces of software. But creating little pieces of software was already available, for example I make most of my DIY software in a spreadsheet. There are tons upon tons of low code possibilities or already existing software packages that need a bit of configuration that one can use and using AI or LLM's is not bringing anything that is revolutionizing access to computation o…
Earlier quoted context omitted.
The crucial part is security. If the apps runs locally it doesn’t matter, if it‘s connected to the net it could be the seed for the next Mirai bot network.
Also design. All the vibe coded apps always look like absolute ass.
Earlier quoted context omitted.
Author here. I agree with this comment, but if I wrote more like this my blog post would get less traction. "LLM coding tools are search-based program synthesizers," in my mind this is what compilers are. I think most compilers do far too little search and opt for heuristics instead, often because they don't have an integrated runtime environment, but it's the same idea. "Plenty of effective engineering tools are sto…
In your blog post: “Most people do not care to find the truth, they care about what pumps their bags” in your HN comment: “I agree with this comment, but if I wrote more like this my blog post would get less traction.” Seems like you also not care about the truth.
It's not a "compiler," it's a "probabilistic code synthesizer guided by your constraints"
The latter is technically more specific and correct than the former, but it's 7 words instead of 1. And the word compiler is understood to encompass the latter, even if most compilers aren't that. They are both "a tool in a workflow"
Earlier quoted context omitted.
Author here. I agree with this comment, but if I wrote more like this my blog post would get less traction. "LLM coding tools are search-based program synthesizers," in my mind this is what compilers are. I think most compilers do far too little search and opt for heuristics instead, often because they don't have an integrated runtime environment, but it's the same idea. "Plenty of effective engineering tools are sto…
In your blog post: “Most people do not care to find the truth, they care about what pumps their bags” in your HN comment: “I agree with this comment, but if I wrote more like this my blog post would get less traction.” Seems like you also not care about the truth.
Earlier quoted context omitted.
The Internet is awash with people making the same claims you are, but where are the actual results that we can see and use? Where are all these supposed new programs that were only possible to make because of generative ai? The number of new apps in the app store is flat. Still getting the same amount in 2025 as in 2022.
App-store listing is a whole other animal. I don't care to go through all that just to share my app. I also don't care to resolve every technical issue others experience. Every time I've thought about generating revenue by selling my apps, two thoughts come to mind: my code is not professional-grade, and the field is so competitive than within months a professional will likely create a better app so why pollute the w…
I'm almost 50, and have been writing code professionally since the late 90s. I can pretty much see projects in my head, and know exactly what to build. I also get paid pretty well for what I do. You'd think I'd be the prototype for anti-AI. I'm not. I can build anything, but often struggle with getting bogged down with all the basic work. I love AI for speed running through all the boring stuff and getting to the goo…
Analogies to humans don't work that well. AI is super-human in some respects while also lacking the ability to continually work toward a goal over long periods of time. AI can do very little on its own - just short / scoped / supervised tasks.
However, sometimes the situation is reversed, AI is the teacher who provides some examples on how to do things or provides hints on how to explore a new area and knows how others have approached similar things. Then, sometimes, AI is an astute code reviewer, typically providing valuable feedback.
Anyway, I've stopped trying anthropomorphize AI and simply try to reason about it based on working with it. That means combinations of direct ChatGPT usage with copy / paste / amend type workflows, async style / full PR style usage, one-shot "hail Mary" type throw away PRs just to establish an initial direction as well as PR reviews of my own code. I'm using AI all the time, but never anything like how I would work with another human.