My experience with generative-AI has been that, at its very best, it is subtly wrong in ways that only an expert in the relevant subject would recognise.
-
You know what? HyperCard was a glorious moment in time that I dearly miss: an army of non-experts were bashing together and sharing weird and wonderful stacks that were part 'zine, part adventure game and part database. Instead of laughing at vibe-coders, maybe we should ask ourselves why the current state-of-the-art in beginner-friendly programming tools is a planet-boiling roulette wheel.
@jonathanhogg lazarus still exists, as a faint remanent of those times
-
@jonathanhogg @jarkman Ack. Having now watched, I think your Alpaca talk is a pretty good intro. I see some resonance in your approach with OpenSCAD (different goals, of course).
-
I will say one thing for generative AI: since these tools function by remixing/translating existing information, that vibe programming is so popular demonstrates a colossal failure on the part of our industry in not making this stuff easier. If a giant ball of statistics can mostly knock up a working app in minutes, this shows not that gen-AI is insanely clever, but that most of the work in making an app has always been stupid. We have gatekeeped programming behind vast walls of nonsense.
@jonathanhogg that's an interesting take. wouldn't that mean the same applies to art then?
Software development is in my opinion a creative task, and "AI" has shown that people will take shortcuts to get "results" faster just to get the recognition. I think the problem might be more in impatience and how our society doesn't allow things to take time.
-
@jonathanhogg @jarkman Ack. Having now watched, I think your Alpaca talk is a pretty good intro. I see some resonance in your approach with OpenSCAD (different goals, of course).
-
We seem to have largely stopped innovating on trying to lower barriers to programming in favour of creating endless new frameworks and libraries for a vanishingly small number of near-identical languages. It is the mid-2020s and people are wringing their hands over Rust as if it was some inexplicable new thing rather than a C-derivative that incorporates decades old type theory. You know what I consider to be genuinely ground-breaking programming tools? VisiCalc, HyperCard and Scratch.
-
@dasgrueneblatt I think you have misunderstood me: I think vibe coding is a horrendous problem, but it is a symptom of an industry failing. That people are trying to steer a tank with a speak'n'spell is because we have not made decent bikes.
" That people are trying to steer a tank with a speak'n'spell is because we have not made decent bikes." -- if we look at the real-world situation of your metaphor, we see that when "decent bikes" ARE finally here, the establishment begins to gatekeep and legislate against them /because/ they are too effective, at overturning the status quo - ostensibly on the grounds that they are "dangerous" when in the wrong hands.
Wondering if the analogy feeds back in the other direction too.
-
@jonathanhogg that's an interesting take. wouldn't that mean the same applies to art then?
Software development is in my opinion a creative task, and "AI" has shown that people will take shortcuts to get "results" faster just to get the recognition. I think the problem might be more in impatience and how our society doesn't allow things to take time.
@codingcatgirl Thanks for this! As someone who has also called themself an artist for over a decade, I have a lot of thoughts on this too, but perhaps I need to mull for a bit and then start a new thread. I’ll drop you a link when I start posting
-
You know what? HyperCard was a glorious moment in time that I dearly miss: an army of non-experts were bashing together and sharing weird and wonderful stacks that were part 'zine, part adventure game and part database. Instead of laughing at vibe-coders, maybe we should ask ourselves why the current state-of-the-art in beginner-friendly programming tools is a planet-boiling roulette wheel.
@jonathanhogg Scratch is excellent. My kid's been using it. I used hypercard at his age and it was a lot fun.
Had it not been because our teacher had acquired two macs into the class, and we could spend time before and after school, I don't think it would have been as fun. It's not just the tools, but also the environment and culture.
-
@jarkman @jonathanhogg Several years ago, I played around with using Haskell as a substrate for a DSL. Used a combinator parser (Parsec) to spit out a directly executable “compiled” function. I’ve occasionally thought it would be fun to do something similar for CSG.
-
@jarkman @jonathanhogg Several years ago, I played around with using Haskell as a substrate for a DSL. Used a combinator parser (Parsec) to spit out a directly executable “compiled” function. I’ve occasionally thought it would be fun to do something similar for CSG.
-
My experience with generative-AI has been that, at its very best, it is subtly wrong in ways that only an expert in the relevant subject would recognise. So I don't worry about us creating super-intelligent AI, I worry about us allowing that expertise to atrophy through laziness and greed. I refuse to use LLMs not because I'm scared of how clever they are, but because I do not wish to become stupider.
@jonathanhogg At worst, it's screamingly wrong in a way that only someone knowledgeable will recognize. Thus chatbots become a source of disinformation.
-
@jonathanhogg Afterward:
The program manager eventually left the company, and the team immediately rewrote the editor in Java/Swing. It took a summer, but now the company could brag that it used Java exclusively to write tools for Java.
I certainly never met a customer who cared whether the editor was written in Java. For that matter, nobody cared that the core analysis engine was written in C++.
Programming is a pop culture.
@raganwald @jonathanhogg Well... The only reason I would care if the editor is written in Java vs Electron vs C++ is that I would notice how the memory got hogged, or the UI would think for minutes, or - rarely - it would be almost immediate (albeit missing half of the features and sometimes crashing completely).
-
@raganwald @jonathanhogg Well... The only reason I would care if the editor is written in Java vs Electron vs C++ is that I would notice how the memory got hogged, or the UI would think for minutes, or - rarely - it would be almost immediate (albeit missing half of the features and sometimes crashing completely).
@rojun There were legitimate business reasons for having as much as possible written in Java that the program manager supported, but shipping means deciding which good ideas to turn down so that other good ideas are executed well. And while the program manager was in charge, leadership agreed.
-
Sixteen Claude AI agents working together created a new C compiler
The $20,000 experiment compiled a Linux kernel but needed deep human management.
Ars Technica (arstechnica.com)
-
My experience with generative-AI has been that, at its very best, it is subtly wrong in ways that only an expert in the relevant subject would recognise. So I don't worry about us creating super-intelligent AI, I worry about us allowing that expertise to atrophy through laziness and greed. I refuse to use LLMs not because I'm scared of how clever they are, but because I do not wish to become stupider.
@jonathanhogg I use AI once in a great while to speed thing up.
I tend to learn things from it as well. Log locations. Quick error retrieval.
Error diagnosis. I know how to do this anyway and knowing the nomenclature and pointing AI in the correct direction is quite useful.I do not use it to WORK FOR ME. I use it in collaboration. It will break sh!t on its own. Either way its coming like it or not.
Moderation is key. Many things can make you stupid.
Gen AI is quite far away.
-
On the gripping hand, if you're a trained programmer using vibe-coding because of a perceived increase in your productivity, or pressure from management to increase your productivity, I would refer you to my first post in this thread…
I've seen lots of posts in the last couple of days about how quickly one can write lots of code with AI. I feel perplexed by this as I hate large programs. The largest thing I have written in the last decade is Flitter. It's only 30k lines and I believe very strongly that it is. Still. Too. Big. Even there, I wrote it purposely to allow the stuff I write *in* it to be very smol: mostly no more than 100 lines. That is the maximum I want to write in a day.
-
I've seen lots of posts in the last couple of days about how quickly one can write lots of code with AI. I feel perplexed by this as I hate large programs. The largest thing I have written in the last decade is Flitter. It's only 30k lines and I believe very strongly that it is. Still. Too. Big. Even there, I wrote it purposely to allow the stuff I write *in* it to be very smol: mostly no more than 100 lines. That is the maximum I want to write in a day.
To me, all these people crowing about having written 10k lines of code in a day are idiots. If you need to write that much code in a day, you are manifestly working at the wrong level of abstraction to solve your problem.
-
I've seen lots of posts in the last couple of days about how quickly one can write lots of code with AI. I feel perplexed by this as I hate large programs. The largest thing I have written in the last decade is Flitter. It's only 30k lines and I believe very strongly that it is. Still. Too. Big. Even there, I wrote it purposely to allow the stuff I write *in* it to be very smol: mostly no more than 100 lines. That is the maximum I want to write in a day.
@jonathanhogg I feel like this misses the point. The point is to not have to spend your life writing 100 lines in a day, when the end goal can be achieved faster and still be as good if not better than hand-made. I am not saying there are no issues and that there is no slop. I am saying it requires mind shift and learning in order for it to not produce slop. Otherwise it will produce results like in your first reply. If coding is just a hobby for you, then none of this matters anyways.
-
I've seen lots of posts in the last couple of days about how quickly one can write lots of code with AI. I feel perplexed by this as I hate large programs. The largest thing I have written in the last decade is Flitter. It's only 30k lines and I believe very strongly that it is. Still. Too. Big. Even there, I wrote it purposely to allow the stuff I write *in* it to be very smol: mostly no more than 100 lines. That is the maximum I want to write in a day.
@jonathanhogg Consider this scenario: spend a very long time planning and designing, and then have a very fast code output, then fix any issues.
Also what about projects which can't be made in 30k lines? Doesn't automatically mean that the project is wrong just because it is big.
-
To me, all these people crowing about having written 10k lines of code in a day are idiots. If you need to write that much code in a day, you are manifestly working at the wrong level of abstraction to solve your problem.
@jonathanhogg
We need more done in actually high level languages.
