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

Show HN: Huzzah – a novel approach to coding with AI

danielvaughn.dev

Post reply on HN
Print view View original

181–190 of 195 posts

Re: Show HN: Huzzah – a novel approach to coding with AI

#181

Post by r0ze-at-hn »

danielvaughn wrote: post #37
r0ze-at-hn wrote: post #29

> There’s no reliable record of human intent. Every engineer I have ever mentored got a lesson on how to write a good commit message that included this. This is exactly that. Further Huzzah from skimming it over seems to be re-inventing documenting your code. Together I can only surmise that the author is new out of school or has simply not yet worked on a team with good coding practices.

A good commit message is not a record of human intent, it's a record of changes in human intent. You can read a change log to see the evolution of a codebase, sure. But before AI arrived on the scene, source code was a single artifact that directly expressed the intended behavior of a piece of software as it currently exists. After AI, the artifact is still there, but it's no longer the true record of human intent.

A good commit message will survive longer than this proposal is the point.

What the author is proposing has a long history of similar ideas: Literate Programming, UML modeling, DSL crazes, and now to LLM-generated abstractions. AI isn't special. They always fail in the same ways as basic "commenting your code". One can even argue that unit tests are a close cousin to this same problem. Taken one step further how is Huzzah better than just using property tests?

Re: Show HN: Huzzah – a novel approach to coding with AI

#182

Post by Jataman606 »

For a long time now i thought that AI tooling went wrong way. Or at least it went way that makes sense from valuation and selling business point of view, instead of what actually would make developers better at their jobs point of view. We started with chats then someone invented harness which is just chat window with few additions and it separated us from actual code.

It makes sense if you want to sell a dream that now everyone can become developer and it is cool that non-tech people can now generate todo apps tailored for they own use. But when working on complex project, that is used by real paying customers you need to be responsible for the code you are producing no matter if it was written by AI or by hand.

Thats why i think we would be better with deep integration with IDEs instead of having separate window I need to alt-tab to to do something. I really liked first approaches (IIRC first release of Copilot worked like that) where you put comment inside code describing what function you need and AI would just fill it in. That way developer is still in charge of what is happening. For bigger tasks create new file and describe what should be happening and let AI go wild with it, splitting work into more files as needed.

Currently Jetbrains kinda supports that flow but it is clear that it is not their main focus, so I find it kinda lacking.

Re: Show HN: Huzzah – a novel approach to coding with AI

#183

Post by danielvaughn »

andai wrote: post #145
avaer wrote: post #36

I think the reverse direction is more important: taking a massive complex problem/codebase and decomposing it to short pseudocode. Then you could edit the pseudocode and compile it back into the system. That's the way software engineers working on large projects work anyway: you first gather context on the state of the system and read it at a level you can understand. Then you propose a change on the simplified repre…

I had a LLM based prototype called "cleanroom" which would convert a program into a spec and then back into a program. The results were disgusting: the spec would encode all sorts of irrelevant implementation details, and then the new version would reimplement them faithfully, and be 3x more bloated than the original. The exact opposite of what I was going for! I didn't put much effort into it, maybe it was solvable…

This largely matches my experience, and was one of the motivators behind this project. For some reason, LLMs are still very bad at distillation. We had a really large and complex codebase at my job that I had to quickly ramp up on. I asked an LLM to generate product docs from it, and it barely helped me.

I came to the conclusion that something in the codebase needs a hard boundary, where the team agrees that only human hands touch it. Otherwise the entire repo becomes untrustworthy as far as discovering intent goes.

Re: Show HN: Huzzah – a novel approach to coding with AI

#184

Post by wccrawford »

projektfu wrote: post #118
wccrawford wrote: post #102

Earlier quoted context omitted.

The AIs can read images and charts. If you want to try programming with UML, you should absolutely try it. My guess is that you'll initially be absolutely gobsmacked, but then the problems will start to show and it'll be frustrating as well.

Let's be honest, programmers can't program from UML specs.

Yeah. I think it'd be fun to watch an LLM try, though. I'm imagining that it'll really show all the things in the UML that don't fully make sense, but look great at first.

Re: Show HN: Huzzah – a novel approach to coding with AI

#185

Post by danielvaughn »

ygouzerh wrote: post #168
ern wrote: post #70

Earlier quoted context omitted.

I have to admit, I am unsure if this article was some sort of parody.

Same, I am still thinking that it's a parody: going full loop back to programming

Basically yes that’s what I’m proposing. Not sure if I’d describe it as a loop though - more like returning to some midway point after having traveled too far in one direction.

Fully manual coding is the most reliable but extremely slow and costly.

Fully LLM driven coding is extremely fast, but for serious work is too unreliable.

Spec-driven development might be viable, but too often the specs end up being LLM maintained, which defeats the purpose.

You need some hard boundary in the codebase where only human hands touch the files. And you want to enable the velocity that AI allows. So yes, semi-formal programming does seem like a promising solution.

Re: Show HN: Huzzah – a novel approach to coding with AI

#186

Post by lelanthran »

reticulates wrote: post #80
darthcircuit wrote: post #69

Earlier quoted context omitted.

I would disagree that there is no thinking. I think a strong understanding of the fundamentals of coding are still wildly important to get good quality code, and a big part of that is thinking or reasoning through a particular problem. It’s just now we have a way of using common language in order for that to happen instead of having to learn or keep up with every new tool and framework in order to do so. The new prog…

I don’t mean to imply that making things with these tools is lesser, or that it doesn’t require some skill, but it is fundamentally different to programming. I’m glad you’re able to bring new things to life with these tools, that’s a great thing :) My broader philosophical take is that we, programmers, lived through a golden age where our skills used on our terms were some of the most valuable skills. The golden age…

> I don’t mean to imply that making things with these tools is lesser, or that it doesn’t require some skill,

But it doesn't require some skills. People have posted showing their 7 year old turning out some game using AI; if your software requires the literacy of the average 7 year old to produce some target, trust me - it doesn't require skills.

Re: Show HN: Huzzah – a novel approach to coding with AI

#189

Post by fzeindl »

reticulates wrote: post #47

I think you’re probably missing why it’s exhausting. The problem is not writing English, it’s the rate of change. Programming is meditative, it is a thinking process, the code you output is an artifact of your thinking. Agent-based development… there is no thinking, no meditation, you’re delegating the thinking to a machine, you’re just barking what you want at it, incessantly, endlessly. For businesses it makes sens…

From a great lecture on agentic SLDC:

„Checking the work is not the same as doing the work.“

It‘s different. There are people who love coding but don‘t like checking written code. Or the other way around.

Also there’s difference in mental load: checking a finished program or algorithm can be harder than working through it while producing it.

Re: Show HN: Huzzah – a novel approach to coding with AI

#190

Post by lofaszvanitt »

JrProgrammer wrote: post #175
lofaszvanitt wrote: post #171

It's tiring to see how people in the seemingly know dance around the issues an noone gets to the point, noone solves anything.

What is your solution to this problem? Surely ranting about it online isn't going to help?

This isn't a rant, this is an observation or conclusion. I'm amused how clueless people really are. I mean, it's mind boggling how vast the desert of the emptymindedness is in this forum.

My solution? I'm waiting for someone to make it, since I'm lazy... until then that's my secret.

Post reply on HN