Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

With AI you need to think bigger

rodyne.com

Post reply on HN
Print view View original

111–120 of 182 posts

Re: With AI you need to think bigger

#111

Post by Workaccount2 »

someothherguyy wrote: post #98
xrd wrote: post #92

Where are the LLM leaderboards for software estimation accuracy? I have been using Claude Code and Aider and I do think they provide incredibly exciting potential. I can spin up new projects with mind boggling results. And, I can start projects in domains where I previously had almost no experience. It is truly exciting. AND... The thing I worry most about is that now non-technical managers can go into Claude and say…

> I can spin up new projects with mind boggling results Boggle a skeptical mind

I used claude to create a piece of software that can render gerber files (essentially vector files used in electronics manufacturing), overlay another gerber file on top of it with exact alignment, and then provide a GUI for manually highlighting components. The program then calculates the centroid, the rotation, and prompts for a component designator. This all then gets stored in a properly formatted Place file, which is used for automating assembly.

The day before this I was quote $1000/yr/user for software that could do this for us.

Re: With AI you need to think bigger

#112

Post by soperj »

nineplay wrote: post #110
CaffeineLD50 wrote: post #97

I had a minor desire to make a feature that had a slightly higher effort than reward, so although I knew I could struggle it out I didn't bother. After years of this I decided to give an AI a shot at the code. It produced something plausible looking and I was excited. Was it that easy? The code didn't work. But the approach made me more motivated to look into it and I found a solution. So although the AI gave me crap…

One of my more effective uses of AI is for rubber duck debugging. I tell it what I want the code to do, iterate over what it comes back with, adjust the code ( 'now rewrite foo() so 'bar' is is passed in'). What comes back isn't necessarily perfect and I don't blindly copy and paste but that isn't the point. At the end I've worked out what I want to do and some of the tedious boiler-plate code is taken care of.

I've tried it, and ended up with the completely wrong approach, which didn't take that long to figure out, but still wasted a good half hour. Would have been horrible if i didn't know what I was doing though.

Re: With AI you need to think bigger

#113

Post by Verdex »

keeptrying wrote: post #25
klabb3 wrote: post #13

As a mostly LLM-skeptic I reluctantly agree this is something AI actually does well. When approaching unfamiliar territory, LLMs (1) use simple language (improvement over academia but also much professional intentionally obfuscated literature), (2) use the right abstraction (they seem good at ”zooming out” to big picture of things, and (3) you can move both laterally between topics and ”zoom in” quickly. Another way…

Yes. LLMs are the perfect learning assistant. You can now do literally anything. Literally. Going to take a while for everyone to figure this out but they will given time.

I don't know. I wouldn't trust a brain surgeon who has up til now only been messing around on LLMs.

Edit: and for that matter I also would not trust a brain surgeon who had only read about brain surgery in medical texts.

Re: With AI you need to think bigger

#114

Post by aaalll »

xrd wrote: post #92

Where are the LLM leaderboards for software estimation accuracy? I have been using Claude Code and Aider and I do think they provide incredibly exciting potential. I can spin up new projects with mind boggling results. And, I can start projects in domains where I previously had almost no experience. It is truly exciting. AND... The thing I worry most about is that now non-technical managers can go into Claude and say…

There is a tool cool lovable that is basically targeted at that exact thing having designers and product managers get something that kinda works

Re: With AI you need to think bigger

#115

Post by gopalv »

nineplay wrote: post #110
CaffeineLD50 wrote: post #97

I had a minor desire to make a feature that had a slightly higher effort than reward, so although I knew I could struggle it out I didn't bother. After years of this I decided to give an AI a shot at the code. It produced something plausible looking and I was excited. Was it that easy? The code didn't work. But the approach made me more motivated to look into it and I found a solution. So although the AI gave me crap…

One of my more effective uses of AI is for rubber duck debugging. I tell it what I want the code to do, iterate over what it comes back with, adjust the code ( 'now rewrite foo() so 'bar' is is passed in'). What comes back isn't necessarily perfect and I don't blindly copy and paste but that isn't the point. At the end I've worked out what I want to do and some of the tedious boiler-plate code is taken care of.

> some of the tedious boiler-plate code is taken care of.

For me that is the bit which stands out, I'm switching languages to TypeScript and JSX right now.

Getting copilot (+ claude) to do things is much easier when I know exactly what I want, but not here and not in this framework (PHP is more my speed). There's a bunch of stuff you're supposed to know as boilerplate and there's no time to learn it all.

I am not learning a thing though, other than how to steer the AI. I don't even know what SCSS is, but I can get by.

The UI hires are in the pipeline & they should throwaway everything I build, but right now it feels like I'm making something they should imitate in functionality/style better than a document, but not in cleanliness.

Re: With AI you need to think bigger

#116

Post by epiccoleman »

nineplay wrote: post #110
CaffeineLD50 wrote: post #97

I had a minor desire to make a feature that had a slightly higher effort than reward, so although I knew I could struggle it out I didn't bother. After years of this I decided to give an AI a shot at the code. It produced something plausible looking and I was excited. Was it that easy? The code didn't work. But the approach made me more motivated to look into it and I found a solution. So although the AI gave me crap…

One of my more effective uses of AI is for rubber duck debugging. I tell it what I want the code to do, iterate over what it comes back with, adjust the code ( 'now rewrite foo() so 'bar' is is passed in'). What comes back isn't necessarily perfect and I don't blindly copy and paste but that isn't the point. At the end I've worked out what I want to do and some of the tedious boiler-plate code is taken care of.

I had some results last week that I felt were really good - on a very tricky problem, using AI (Claude 3.7) helped me churn through 4 or 5 approaches that didn't work, and eventually, working in tandem, "we" found an approach that would. Then the AI helped write a basic implementation of the good approach which I was able to use as a reference for my own "real" implementation.

No, the AI would not have solved the problem without me in the loop, but it sped up the cycle of iteration and made something that might have taken me 2 weeks take just a few days.

It would be pretty tough to convince me that's not spectacularly useful.

Re: With AI you need to think bigger

#117

Post by dartos »

gopalv wrote: post #115
nineplay wrote: post #110

Earlier quoted context omitted.

One of my more effective uses of AI is for rubber duck debugging. I tell it what I want the code to do, iterate over what it comes back with, adjust the code ( 'now rewrite foo() so 'bar' is is passed in'). What comes back isn't necessarily perfect and I don't blindly copy and paste but that isn't the point. At the end I've worked out what I want to do and some of the tedious boiler-plate code is taken care of.

> some of the tedious boiler-plate code is taken care of. For me that is the bit which stands out, I'm switching languages to TypeScript and JSX right now. Getting copilot (+ claude) to do things is much easier when I know exactly what I want, but not here and not in this framework (PHP is more my speed). There's a bunch of stuff you're supposed to know as boilerplate and there's no time to learn it all. I am not lea…

The idea of untangling AI generated typescript spaghetti fills me with dread.

It’s as bad as untangling the last guy’s typescript spaghetti. He quit, so I can’t ask him about it either.

Re: With AI you need to think bigger

#118

Post by magic_hamster »

haswell wrote: post #24

I recently discovered that some of the Raspberry Pi models support the Linux Kernel's "Gadget Mode". This allows you to configure the Pi to appear as some type of device when plugged into a USB port, i.e. a Mass Storage/USB stick, Network Card, etc. Very nifty for turning a Pi Zero into various kinds of utilities. When I realized this was possible, I wanted to set up a project that would allow me to use the Pi as a b…

> Instead it took a few hours, and I finished a project.

Did you?

If you wanted to expand on it, or debug it when it fails, do you really understand the solution completely? (Perhaps you do.)

Don't get me wrong, I've done the same in the last few years and I've completed several fun projects this way.

But I only use AI on things I know I don't care about personally. If I use too much AI on things I actually want to know, I feel my abilities deteriorating.

Re: With AI you need to think bigger

#119

Post by smhinsey »

It seems like the emphasis on getting results in one shot reduces the maximum potential quality of the output as compared to a more incremental approach. For example, create an initial prompt to generate a structured description of the features in the program you've described. You can then iterate on this and follow up with a prompt that generates a structured description of a system architecture based on the feature description, and iterate on that. You could build up other informational layers as well, before aggregating all that structural data into the generation of the actual code. This can feed into the generation of tests as well.

If you look at things like LLM party for comfyui, it's the same basic concept.

Re: With AI you need to think bigger

#120

Post by golergka »

CaffeineLD50 wrote: post #97

I had a minor desire to make a feature that had a slightly higher effort than reward, so although I knew I could struggle it out I didn't bother. After years of this I decided to give an AI a shot at the code. It produced something plausible looking and I was excited. Was it that easy? The code didn't work. But the approach made me more motivated to look into it and I found a solution. So although the AI gave me crap…

> I decided to give an AI

What model? What wrapper? There's just a huge amount of options on the market right now, and they drastically differ in quality.

Personally, I've been using Claude Code for about a week (since it's been released) and I've been floored with how good it is. I even developed an experimental self-developing system with it.

Post reply on HN