Yes, many tools work like that, especially professional tools.
You think you can just fire up Ableton, Cubase or whatever and make as great music as a artist who done that for a long time? No, it requires practice and understanding. Every tool works like this, some different difficulties, some different skill levels, but all of them have it in some way.
This is the company making the tool that is holding the tool, in this case, claiming that "[they] built a browser" when, if TFA's assertions are correct, they did not "build a browser" by any reasonable interpretation of those words.
(I grant that you're speaking from your experience, about different tools, two replies up, but this claims is just paper-rock-scissorable through these various AI tools. "Oh, this tool's authors are just hype, but this tool works totes-mc-oates…". Fool me once, and all.)
Yes, and apparently is a horrible way, because they've obviously failed to produce a functioning browser. But since I'm the author of TFA, I guess I'm kind of biased in this discussion.
Codex was sold to me as a tool that can help me do program. I tried it, evaluated it, found it helpful, continued using it. Based on my experience, it definitively helps with some tasks. Apparently also, it does not work for others, for some not at all. I know the tool works for me, and I take the claim that it doesn't for others, what am I left to believe in? That the tool doesn't actually work, even though my own experience and usage of it says otherwise?
Codex is still an "AI success", regardless if it could build an entire browser by itself, from scratch, or whatever. It helps as it is today, I wouldn't need it to get better to continue using it.
But even with this perspective, which I'd say is "nuanced" (others would claim "AI zealot" probably), I'm trying to see if what Cursor claims is actually true, that they managed to build a browser in that way. When it doesn't seem true, I call it out. I still disagree with "This is what most AI "successes" turn out to be when you apply even a modicum of scrutiny", and I'm claiming what Cursor is doing here is different.
Not even the Ableton marketing team is telling me I can just fire up Ableton and make great music and if I can't do that I must be a brainwashed doomer.
The argument isn't what OpenAI/Anthropic are selling their users, what I said was:
> are definitively capable tools when used in certain ways
Which I received pushback on. My reply is to that pushback, defending what I said, not what others told you.
Edit: Besides the point, but Ableton (and others) constantly tell people how to learn how to use the tool, so they use it the right way. There is a whole industry of people (teachers) who specialize in specific software/hardware and teaching others "how to hold the tool correctly".
> Besides the point, but Ableton (and others) constantly tell people how to learn how to use the tool, so they use it the right way
It's just an odd comparison to begin with. You said
> You think you can just fire up Ableton, Cubase or whatever and make as great music as a artist who done that for a long time
I don't think you have to be good at Ableton at all to make good music. I don't think you can even argue it would benefit your music to learn Ableton. There's a crap ton of people who are wizards with their DAW making mediocre music. A DAW can be fun to learn, and that can help me keep my flow state. But it's not literally going to make better music, and the fundamentals of production don't change at all from DAW to DAW.
That's a totally separate thing from LLMs. We are constantly told that if we learn the magic way to use LLMs, we can spit out functioning code a lot faster. But in reality, people are just generating code faster than they can verify it.
> That's a totally separate thing from LLMs. We are constantly told that if we learn the magic way to use LLMs, we can spit out functioning code a lot faster. But in reality, people are just generating code faster than they can verify it.
I don't see it as it is. LLMs are not magically gonna make you be able to produce high-quality software, just like Ableton isn't gonna magically gonna make you be able to produce high-quality music. But if you learn the tool, it gets a lot easier to use effectively. And the better you are at "producing high quality music/code", probably the more use you can make of Ableton/LLMs, compared to someone who aren't good at those things already.
Again, what you're being told by other people, I don't know, and frankly don't really care. OpenAI sold Codex to me as a tool that can help me, a programmer, do programming, and that's exactly what that tool gives me.
Cursor in their article tried to sell their tool as something that can "Hundreds of agents can work together on a single codebase for weeks, making real progress on ambitious projects" which I claim in TFA, doesn't seem to be true.
> "definitively capable tools when used in certain ways". This sounds like "if it doesn't work for you is because you don't use in the right way" imo.
Yes, because that's what it is. If you seriously can't get Gemini 3 or Opus 4.5 to work you're either using it wrong or coding on something extremely esoteric.
Efficiency will ultimately decide if LLMs become feasible long-term. Right now, the LLM industry is not sustainable. Investors were promised literally the future in the present and it is now undeniable that ASI, AGI or even moderately competent general purpose quasi-autonomous systems won't happen anytime soon. The reality is that there is not space for all these players in the market in the long-term. LLMs won't go away but the vast majority of mainstream providers will definitely do
This is HN, a place where people see dot A and people see dot B but they fail to connect the dots. Reminds me of HN's underwhelming reaction to Dropbox.
One would think that travelling across so many countries and continents would be quite clearly the point of the bus service.
I've given up on expecting any subtlety or nuance from the painfully literal nerds on here. "Must optimize my route for efficiency because I am an engineer! No fun allowed!" There's a certain depressing lack of joie de vivre.
It's not nerdism. It's the dominant ideology of our times - neoliberalism - which demands that everything be valued only in terms of dollars. A trip that takes 50 days is not dollar efficient because you could fly in one day and spend the remaining 49 days earning dollars, i.e. the value of time is only about dollars, and cannot be other measures, especially subjective ones like human enjoyment and wonder.
The name just popped into my head as I was sitting there looking at the main page, I saw how one idea can need multiple tools, like the rays of a prism relying on a single beam of light.
Churning out 2x as much code is not doubling productivity. Can you perform at the same level as a dev who is considered 2x as productive as you? That's the real metric. Comparing quality to quantity of code ratios, bugs caused by your PRs, actual understanding of the code in your PR, ability to think slow, ability to deal with fires, ability to quickly deal with breaking changes accidentally caused by your changes.
Churning out more more per day is not the goal. No point merging code that either doesn't fully work, is not properly tested, other humans (or you) cannot understand, etc.
Why is that the real metric? If you can turn a 1x dev into a 2x dev that's a huge deal, especially if you can also turn the original 2x dev into a 4x dev.
And far from "churning out code" my work is better with LLMs. Better tested, better documented, and better organized because now I can do refactors that just would have taken too much time before. And more performant too because I can explore more optimization paths than I had time to before.
Refusing to use LLMs now is like refusing to use compilers 20 years ago. It might be justified in some specific cases but it's a bad default stance.
The answer to "Can you perform at the same level as a dev who is considered 2x as productive as you?" is self-explanatory. If your answer is negative, you are not 2x as productive
Seriously, I’m lucky if 10% of what I do in a week is writing code. I’m doubly lucky if, when I do, it doesn’t involve touching awful corporate horse-shit like low-code products that are allergic to LLM aid, plus multiple git repos, plus having knowledge from a bunch of “cloud” dashboard and SaaS product configs. By the time I prompt all that external crap in I could have just written what I wanted to write.
> If one "doesn't know Kubernetes", what exactly are they supposed to do now, having LLM at hand, in a professional setting? They still "can't" asses the quality of the output, after all. They can't just ask the model, as they can't know if the answer is not misleading.
This is the fundamental problem that all these cowboy devs do not even consider. They talk about churning out huge amounts of code as if it was an intrinsically good thing. Reminds me of those awful VB6 desktop apps people kept churning out. Vb6 sure made tons of people nx productive but it also led to loads of legacy systems that no one wanted to touch because they were built by people who didn't know what they were doing. LLMs-for-Code are another tool under the same category.
> someone who’s shipped entire new frontend feature sets, while also managing a team. I’ve used LLM to prototype these features rapidly and tear down the barrier to entry on a lot of simple problems that are historically too big to be a single-dev item, and clear out the backlog of “nice to haves” that compete with the real meat and bread of my business. This prototyping and “good enough” development has been massively impactful in my small org
Has any senior React dev code review your work? I would be very interested to see what do they have to say about the quality of your code. It's a bit like using LLMs to medically self diagnose yourself and claiming it works because you are healthy.
Ironically enough, it does seem that the only workforce AIs will be shrinking will be devs themselves. I guess in 2025, everyone can finally code
I used to hold Karpathy in high esteem. But the stream of posts coming from him since LLMs took over the "AI" word makes me wonder if he has lost the spark
The very concept of people going to a private digital plaza was very problematic in the first place and arguably still is. Humanity's drive towards convenience is the source of marvels but also many ills imo. Google's decline is a chance for change. Change towards something better. Not that I am optimistic that we will get there imo but the opportunity window is opening now. Don't look for a new digital overlord. Embrace the new age
I think that's probably unlikely given the long list of universities using it[0].
It's an educational tool for formal propositional logic which hasn't really changed much on 100 years, so probably not a lot of updates are required unless there are big new updates to Haskell itself.
It seems to of had the web app portion updated a year ago. And as you say, the application itself looks ‘done.’
I have frequently used Common Lisp over the last 40 years, and I hear comments about libraries being old and not updated in many years: so what! Quality code that performs a specific function sometimes is ‘done.’
I am a novice Haskell programmer but I enjoy the language and it is very cool to have the Carnap github repo with a book manuscript, backend and front end code to look over.
Reminds me of SAAP/Salesforce.
reply