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

AI coding is gambling

notes.visaint.space

Post reply on HN
Print view View original

91–100 of 471 posts

Re: AI coding is gambling

#91

Post by nickjj »

thisisbrians wrote: post #41

It is and will always be about: 1) properly defining the spec 2) ensuring the implementation satisfies said spec

> properly defining the spec

Why do you often need to re-prompt things like "can you simplify this and make it more human readable without sacrificing performance?". No amount of specification addresses this on the first shot unless you already know the exact implementation details in which case you might as well write it yourself directly.

I often have to put in a prompt like this 5-10 times before the code resembles something I'd even consider using as a 1st draft base to refactor into something I would consider worthy of being git commit.

I sometimes use AI for tiny standalone functions or scripts so we're not talking about a lot of deeply nested complexity here.

Re: AI coding is gambling

#92

Post by itsgrimetime »

All of this new capability has made me realize that the reason i love programming _isn't_ the same as the OP. I used to think (and tell others) that I loved understanding something deeply, wading through the details to figure out a tough problem. but actually, being able to will anything I can think of into existence is what I love about programming. I do feel for the people who were able to make careers out of falling in love w/ and getting good at picking problems & systems apart, breaking them down, and understanding them fully. I respect the discipline, curiosity, and intellect they have. but I also am elated w/ where things are at/going. this feels absurd to say, but I finally feel like I'm _good_ at programming, which is insane, because I literally haven't written a line of code myself in months, but having tools that can finally match the speed my ideas come to me is intoxicating

Re: AI coding is gambling

#93

Post by sedawkgrep »

copypaper wrote: post #47

You got to know when to Ship it, Know when to Re-prompt, Know when to Clear the Context, And know when to RLHF. You never trust the Output, When you’re staring at the diff view, There’ll (not) be time enough for Fixing, When the Tokens are all spent.

You're a gamblin' man, I see...

Re: AI coding is gambling

#94

Post by CodingJeebus »

acedTrex wrote: post #89
CodingJeebus wrote: post #66

Earlier quoted context omitted.

Personally, I get a huge rush of dopamine seeing LLMs build out complex features very quickly to the point that it will keep me up all night wanting to push further and further. That's where the gambling metaphor really resonates. It's not whether or not the output is correct, I've been building software for many years and I know how direct LLMs pretty well at this point. But I'm also an alcoholic in recovery and I k…

> Personally, I get a huge rush of dopamine seeing LLMs build out complex features very quickly I dont think i've read a sentence on this website i can relate to less. I watch the LLM build things and it feels completely numb, i may as well be watching paint dry. It means nothing to me.

Trust me, I have many days where I wish I had your relationship to this. I wish it were as boring as watching paint dry. But it triggers that part of my brain that wants more, and I have to be very careful about that.

Re: AI coding is gambling

#95

Post by simonw »

lunar_mycroft wrote: post #26
simonw wrote: post #10

Assigning work to an intern is gambling: they're inherently non-deterministic and it's a roll of the dice whether the work they do will be good enough or you'll have to give them feedback in order to get to what you need.

1. Interns learn. LLMs only get better when a new model comes out, which will happen (or not) regardless of whether you use them now. 2. Who here thinks that having interns write all/almost all of your code and moving all your mid level and senior developers to exclusively reviewing their work and managing them is a good idea?

I don't know that the "humans learn, LLMs don't" argument holds any more with coding agents.

Coding agents look at existing text in the codebase before they act. If they previously used a pattern you dislike and you tell them how to do differently, the next time they run they'll see the new pattern and are much more likely to follow that example.

There are fancier ways of having them "learn" - self-updating CLAUDE.md files, taking notes in a notes/ folder etc - but just the code that they write (and can later read in future sessions) feels close-enough to "learning" to me that I don't think it makes sense to say they don't learn any more.

Re: AI coding is gambling

#96

Post by minimaxir »

comboy wrote: post #63

Fascinating how HN is torn about vibe coding still. Everybody pretty much agrees that it works for some use cases, yet there is a flamewar (I mean, cultured, HN-type one) every time. People seem to be more comfortable in a binary mindset.

> Everybody pretty much agrees that it works for some use cases

That isn't true, which is the exact reason why people have a binary mindset. More than once on Hacker News I've had people accuse me of being an AI booster just because I said I had success with agents and they did not.

Re: AI coding is gambling

#97

Post by gs17 »

Gagarin1917 wrote: post #74

Trying to decide whether to refinance now or not feels like gambling too. Yet it’s financially beneficial to make some bet. Defining “Gambling” like isn’t really helpful.

If I said I had a machine where I put in "tokens", watch it spin, and either get nothing or something valuable (with which I get being largely chance), you'd presume it's some kind of slot machine. The important things IMO are the random chance of getting something and being able to keep retrying so rapidly.

You can't keep paying to play the "refinancing game" until you get a good rate (at least not like pulling the lever again and again, you have to wait a long time, you won't call the same bank again and again, and suddenly they have an amazing rate), it's a different experience and the psychology is different.

Re: AI coding is gambling

#99

Post by Terr_ »

ambicapter wrote: post #59
minimaxir wrote: post #5

The gambling metaphor often applied to vibecoding implies that the outcome cannot be fully controlled or influenced, such as a slot machine. Opus 4.5 and beyond show that it not only can be very much can be influenced, but also it can give better results more consistently with the proper checks and balances.

Slot machines have very controlled results. They are regulated to a high precision of reliability.

I don't think that difference matters to the comparison.

It's not an inherent feature to slot machines, it's something we enforce because people got angry about the outcomes (i.e. fraud) when they didn't operate that way.

It doesn't matter because a dodgy slot-machine is still a slot machine, and the person using it would still be a gambler.

Re: AI coding is gambling

#100

Post by seanmcdirmid »

nickjj wrote: post #91
thisisbrians wrote: post #41

It is and will always be about: 1) properly defining the spec 2) ensuring the implementation satisfies said spec

> properly defining the spec Why do you often need to re-prompt things like "can you simplify this and make it more human readable without sacrificing performance?". No amount of specification addresses this on the first shot unless you already know the exact implementation details in which case you might as well write it yourself directly. I often have to put in a prompt like this 5-10 times before the code resemble…

> I often have to put in a prompt like this 5-10 times before the code resembles something I'd even consider using as a 1st draft base to refactor into something I would consider worth of being git commit.

Are you stuck entering your prompts in manually or do you have it setup like a feedback loop like "beautify -> check beauty -> in not beautiful enough beautify again"? I can't imagine why everyone things AIs can just one shot everything like correctness, optimization, and readability, humans can't one shot these either.

Post reply on HN