Live data from Hacker News

AI coding

geohot.github.io

71–80 of 299 posts

Re: AI coding

#71
post #55
post #48

Earlier quoted context omitted.

I love AI for speed running through all the boring stuff and getting to the good parts. In some cases, especially with the more senior devs in my org, fear of the good parts is why they're against AI. Devs often want the inherent safety of the boring, easy stuff for a while. AI changes the job to be a constant struggle with hard problems. That isn't necessarily a good thing. If you're actually senior by virtue of tim…

>AI changes the job to be a constant struggle with hard problems I find this hilarious. From what I've seen watching people do it, it changes the job from deep thought and figuring out a good design to pulling a lever on a slot machine and hoping something good pops out. The studies that show diminished critical thinking have matched what i saw anecdotally pairing with people who vibe coded. It replaced deep critical…

I think there are two kinds of uses for these tools:

1) you try to explain what you want to get done

2) you try to explain what you want to get done and how to get it done

The first one is gambling, the second one has very small failure rate, at worst, the plan it presents shows it's not getting the solution you want it to do.

Re: AI coding

#72

There is some amount of truth on the AI coding claims. But, what's with the self driving hate? I take Waymos on a regular basis, and he is basing his credibility on the claim that they are not a thing. Makes him sound bitter more than insightful.

George famously started a self driving hardware-as-an-addon company. He started after both claiming self driving was easy, and reportedly taking up an Elon bounty/bet in the seven figure range to make self driving AI for Tesla.

Re: AI coding

#73

> It’s why the world wasted $10B+ on self driving car companies that obviously made no sense. There’s a much bigger market for truths that pump bags vs truths that don’t. Did geohot not found one of these?

Yes. He mentions that in passing that saying people will accuse him of hating on it because he didn't profit from it. I think his point of view is that his company's attempt was smaller scale and not part of the $10B+ waste? In any case I don't fully understand what he's trying to say other than negating the hype (which i generally agree with), but not offering any alternative thoughts of his own other than- we have…

Well, he’s currently running a startup aimed at making better tooling for the space. So, he’s putting his time where mouth is.

Re: AI coding

#74
post #48

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…

I love AI for speed running through all the boring stuff and getting to the good parts. In some cases, especially with the more senior devs in my org, fear of the good parts is why they're against AI. Devs often want the inherent safety of the boring, easy stuff for a while. AI changes the job to be a constant struggle with hard problems. That isn't necessarily a good thing. If you're actually senior by virtue of tim…

That makes me think of https://store.steampowered.com/app/2262930/Bombe/ which is a version of Minesweeper where instead of clicking on squares you define (parametric!) rules that propagate information around the board automatically. Your own rules skip all the easy parts for you. As a result, every challenge you get is by definition a problem that you've never considered before. It's fun, but also exhausting.

Re: AI coding

#75

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…

Would love to see a project you built with the help of AI, can you share any links?

https://github.com/williamcotton/webpipe

Shhh, WIP blog post (on webpipe powered blog)

https://williamcotton.com/articles/introducing-web-pipe

Yes, I wrote my own DSL, complete with BDD testing framework, to write my blog with. In Rust!

  GET /hello/:world
    |> jq: `{ world: .params.world }`
    |> handlebars: `

hello, {{world}}

` describe "hello, world" it "calls the route" when calling GET /hello/world then status is 200 and output equals `

hello, world

`
My blog source code written in webpipe:

http://github.com/williamcotton/williamcotton.com

Re: AI coding

#76

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…

Exactly. I tend to like Hotz, but by his description, every developer is also "a compiler", so it's a useless argument.

My life quality (as a startup cofounder wearing many different hats across the whole stack) would drop significantly if Cursor-like tools [1] were taken away from me, because it takes me a lot of mental effort to push myself to do the boring task, which leads to procrastination, which leads to delays, which leads to frustration. Being able to offload such tasks to AI is incredibly valuable, and since I've been in this space from "day 1", I think I have a very good grasp on what type of task I can trust it to do correctly. Here are some examples:

- Add logging throughout some code

- Turn a set of function calls that have gotten too deep into a nice class with clean interfaces

- Build a Streamlit dashboard that shows some basic stats from some table in the database

- Rewrite this LLM prompt to fix any typos and inconsistencies - yeah, "compiling" English instructions into English code also works great!

- Write all the "create index" lines for this SQL table, so that perform well.

[1] I'm actually currently back to Copilot Chat, but it doesn't really matter that much.

Re: AI coding

#77

Earlier quoted context omitted.

I’m quite sure that there’s a ton more research on it. The drug’s been around for decades. Lots of time for plenty of studies. If legitimate research had found it to be drastically better, that study would definitely have been published in a big way. Unscientifically, I personally know quite a number of folks that sincerely believed that they couldn’t function without it, but have since learned that they do far bette…

My point is that micro-studies like that on a tiny random (or even counter-indicated, "healthy") selection of the general population don't tell you much for drugs that do specific things. "Antibiotics don't improve your life, but can damage your health" would likely be the outcome on 13 randomly selected healthy individuals. But do the same study on 13 people with a bacterial infection susceptible to antibiotics and…

I don't think that it matters, in this context, as a lot of folks here, have their minds made up, already, and won't let anything interfere.

They'll need to learn, the same way I see lots of people learn.

It's been around long enough, though, that all the Adderall-eating people should have established a Gattaca-like "elite," with all us "undermen," scrabbling around at their feet.

Not sure why that never happened...

Re: AI coding

#78
>It’s not precise in specifying things.

That's the point - it's a higher level of abstraction.

>highly non-deterministic

...not unlike say a boss telling a junior to change something?

The bet here isn't that AI can be as precise as something hand coded but rather that you can move up a step in the abstraction layer. To use his compiler example...I don't care what the resulting assembly instructions look like, just whether it works. It's the same thing here just one level higher

Re: AI coding

#79
post #48

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…

I love AI for speed running through all the boring stuff and getting to the good parts. In some cases, especially with the more senior devs in my org, fear of the good parts is why they're against AI. Devs often want the inherent safety of the boring, easy stuff for a while. AI changes the job to be a constant struggle with hard problems. That isn't necessarily a good thing. If you're actually senior by virtue of tim…

Interesting point.

There's also the fact that, while you're coding the easy stuff, your mind is thinking about the hard stuff, looking things up, seeing how they articulate. If you're spending 100% of your time on hard stuff, you might be hurting these preliminaries.

Re: AI coding

#80
I also had a compiler related description come to me after using Copilot. It allows you to partially generate imperative code declaratively, by writing a comment like

//now I will get rows X, Y, Z from ContentsProvider

then tab tab complete. You can then even tweak the generated code, very useful!

Post reply on HN