I've found LLMs decrease the friction in enabling more pedantic lints and tooling. It is a quantity problem because enabling all the aggressive warnings in the compiler makes a lot of work, and its a quality outcome because presumably addressing every warning from the compiler makes the code better
I find that CLI is a great way to model problems. When I find myself doing something that has graduated beyond a comfortable amount of PowerShell, Rust is there for me.
I have a template I've been evolving so it's super easy to get started with something new; I just copy the template and slam Copilot with some rough ideas on what I want and it works out.
Decomposes the problem very nicely into incrementally achievable steps
1. `fetch <username>` to get info from github into a cache location
2. `generate <username> <output.svg>` to load stats and write an svg
3. `serve` to run a webserver to accept GET requests containing the username to do the above
Means that my stuff always has `--help` and `--version` behaviours too
OP here. Unless you're still watching Quibi on your curved TV, delivered via WiMax then, yeah, I'd say it was pretty bloody substantiated.
I like technology. I made a decent living from it. But if I had chased every hyped fad that was promised as the next big thing, I doubt I'd be as happy as I am now.
Just chiming in to say thanks for the Pratchett quote! I dare say he's about to beat out Douglass Adams for my top author. Feets of Clay and Hogfather should be must reads for people dealing with AI right now imo.
You claim to cite 'technologies' but include a few brands and companies for some reason.
The one you keep citing, here and in the article, Quibi, lives on in technology-form (the spirit of your article we must presume) as an 8 billion dollar business in China and is rapidly upending every Hollywood film studio.
So, arguments about substantiation or even 'this time' fall flat in the face of not even understanding your own message.
You're not really saying anything, though. For every tech hype that has failed, there is another that's changed the world. This IS changing the world and our industry, regardless of whether it reaches the heights of the hypers.
I mean you're just stating that sometimes tech doesn't meet it's hype. What's insightful about that? It's a given; cherry-picking examples doesn't prove your case.
The thing is, the successful tech rarely get the excessive hype.
MRNA vaccines. Where are the countless breathless articles about these literal life saving tech? A few, maybe, but very few dudes pumping out asinine "white papers" and trying to ride the hype train.
Solar and battery. Again, lots of real world impact but remarkably few unhinged blowhards writing endless newsletters about how this changes everything.
I'm struggling to think of a tech from the last 20 years which has lived up to its hype.
Not everything is written to be insightful. Some things are just written to get them out of my head.
I personally see plenty of hype but I've also been following the trends and using the tools "on the ground". At least in terms of software these tools are a substantial shift. Will they replace developers? No idea, but their impacts are likely to be felt for a very long time. Their rate of improvement in programming is growing rapidly.
Do feel AI is overall just hype? When did you last try AI tools and what about their use made you conclude they will likely be forgotten or ignored by the mainstream?
I spent an hour with Gemini this morning trying to get instructions to compile a common open source tool for an uncommon platform.
It was an hour of pasting in error messages and getting back "Aha! Here's the final change you need to make!"
Underwhelming doesn't even begin to describe it.
But, even if I'm wrong, we were told that COBOL would make programming redundant. Then UML was going to accelerate development. Visual programming would mean no more mistakes.
All of them are in the coding mix somewhere, and I suspect LLMs will be.
That's the most recent time. But I've bounced around all the LLMs - they're all superficially amazing. But if you understand their output they often wrong in both subtle and catastrophic ways.
As I said, maybe I'm wrong. I hope you have fun using them.
Yes. And, again, they look amazing and make you feel like you're 10x.
But then I look at the code quality, hideous mistakes, blatant footguns, and misunderstood requirements and realise it is all a sham.
I know, I know. I'm holding it wrong. I need to use another model. I have to write a different Soul.md. I need to have true faith. Just one more pull on the slot machine, that'll fix it.
The web? GLP-1s? 5G? The newton was mega-hyped, failed but Apple came back with the iPhone. All the dot com failures that eventually became viable businesses (so viable in-fact that sfgate has to reach back 26 years to write their stinkpiece [1])
Hype is often early, in 10-20 years we'll start seeing the value as the rest of the world catches up
Why do you think that solar+battery technology or MRNA vaccines haven't been written about in excited, hype-filled ways? If a technology is successful, then looking at past accounts of that technology and why it will change the world don't come across to you reading it now as hype, they come across as a description of something normal about the world.
It's not unsubstantiated though. The claim is "People frequently assert that 'this time is different' and they are almost always wrong" and it proceeded to provide a reasonable list of analogous manias.
This only doesn't feel like substantiation if you reject the notion that these cases are analogous.
"You shouldn't eat that."
"Why not?"
"Everyone else who's eaten it has either died or gotten really sick."
"But I'm different! Why should I listen to your unsubstantiated claims?"
"(lists names of prior victims)"
"That doesn't mean anything. I'm different. You're just making vague and dismissive unsubstantiated claims."
The claim isn't "AI bad" the claim is more along the lines of "there's a lot of money changing hands and this has all the earmarks of a classic hype cycle; while attention/diffusion models may amount to something the claims of their societal impacts are almost certainly being exaggerated by people with a financial stake in keeping the bubble inflated as long as possible, to pull in as many suckers as possible."
If you want another example (which you won't find analogous if you've already drunk the koolaid):
for 50,000 rows I'd much rather just use fzf/nucleo/tv against json files instead of dealing with database schemas.
When it comes to dealing with embedding vectors rather than plaintext then it gets slightly more annoying but still feels like such an pain in the ass to go full database when really it could still be a bunch of flat open files.
More of a perspective from just trying to index crap on my own machine vs building a SaaS
Thanks! I have been thinking about opening it up, but not sure, as I've never done any open source stuff and don't know how useful others would find it - there's some clunky bits!
I also have the whole Aider/Claude prompt history in the repo too, as I started this on a platform & framework I'd never used, and used the AI to scaffold much of the app at the beginning. Thought that might be useful to go back and see what worked the best when AI programming.
Python dependency management sucks ass. Installing pytorch with cuda enabled while dealing with issues from the pytorch index having a linux-only version of a package causing shit to fail is endlessly frustrating
A good ecosystem has lockfiles by default, python does not.
reply