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

81–90 of 471 posts

Re: AI coding is gambling

#81

Post by natpalmer1776 »

CodingJeebus wrote: post #66
thisisbrians wrote: post #41

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

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…

It also doesn’t help that producing features is also wired to a sense of monetary compensation. More-so if you’re building a product to sell that might finally be your ticket to whatever your perception of socio-economic victory is.

Re: AI coding is gambling

#82

Post by dzink »

It’s variable rewards and even with large models the same question can lead to dramatically different answers. Possibly because they route your request through different models. Possibly because the model has more time to dig through the problem. Nonetheless we have some illusion of control over the output (you we wouldn’t be playing it) but it is just the quality of the model itself that leads to better outcomes - not your input. If you can’t let go of the feeling thought, it’s definitely addictive. And as I look back, it’s a fast iteration on the building cycle we had before AI. But the brain really likes low latency - it is addicted to the fast reward for its actions. So AI, if it gets fast enough (sub 400ms) it will likely become irreversibly addictive to humans in general, as the brain will see is at part of itself. Hope it has our interest at heart by then.

Re: AI coding is gambling

#83

Post by ryandrake »

RealityVoid wrote: post #39
CraftingLinks wrote: post #30

I see whole teams pushed by c- level going full in with spec driven + tdd development. The devs hate it because they are literally forbidden to touch a single line if code. but the results speak for themselves, it just works and the pressure has shifted to the product people to keep up. The whole tooling to enable this had to be worked out first. All Cursor and extreme use of a tool called Speckit, connected to Notio…

> literally forbidden to touch a single line if code. That is extremely stupid. What does that ban get you? I reqct to this because a friend mentioned exactly this. And I was dumbfounded.

It seems like just a CxO dick measuring exercise.

CEO1: "We allow our engineers to use AI for all work."

CEO2: "Oh yea? We mandate our engineers use AI for at least N% of their work!"

CEO3: "You think that's good? We mandate our engineers use AI for all code!!"

CEO4: "Pfff, amateurs. We don't even allow our engineers to open source code editors or even look at the LLM output..."

Re: AI coding is gambling

#84

Post by vidarh »

rawgabbit wrote: post #52
thisisbrians wrote: post #41

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

I had a CIO tell me 15 years ago with Agile I was wasting my time with specs and design documents.

I was in a call just today where specs were presented as a new thing.

Re: AI coding is gambling

#85

Post by throwmeaway820 »

c_e wrote: post #69
Retr0id wrote: post #11

Earlier quoted context omitted.

Poker is a skill-based game where your actions influence your success, but many people who play it are gambling.

everybody who's playing poker is gambling, skilled or not.

without a rigorous definition of "gambling", such discussions are pointless

Re: AI coding is gambling

#86

Post by reaperducer »

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.

it can give better results more consistently with the proper checks and balances.

You can get more consistent results from a slot machine with a bunch of magnets and some swift kicks. It's still gambling.

Re: AI coding is gambling

#87

Post by CodingJeebus »

natpalmer1776 wrote: post #81
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…

It also doesn’t help that producing features is also wired to a sense of monetary compensation. More-so if you’re building a product to sell that might finally be your ticket to whatever your perception of socio-economic victory is.

That's definitely part of it, sure. I also just get a cosmic kick out thinking about the possibilities that this technology unlocks and that thinking can spiral in all sorts of unhealthy ways.

Re: AI coding is gambling

#88

Post by davidkhess »

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.

One way it works is if you think of cognitive debt as the "house". As in "the house always wins".

Re: AI coding is gambling

#89

Post by acedTrex »

CodingJeebus wrote: post #66
thisisbrians wrote: post #41

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

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.

Re: AI coding is gambling

#90

Post by zer00eyz »

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.

VIM vs Emacs vs IDE vs..., Tabs vs Spaces, Procedural vs OOP vs Functional.

We love a good holy war for sure.

The nuance is lost, and the conversations we should be having never happen (requirements, hiring/skills, developer experience).

Post reply on HN