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

111–120 of 471 posts

Re: AI coding is gambling

#111

Post by Verdex »

DiscourseFan wrote: post #101

When a code doesn't compile, it doesn't kill anyone. But if a Waymo suddenly veers off the road, it creates a real threat. Waymos had to be safer than real human drivers for people to begin to trust them. Coding tools did not have to be better than humans for them to be adopted first. Its entirely possible for a human to make a catastrophic error. I imagine in the future, it will be more likely that a human makes suc…

My understanding is that waymo has gone on the record to say that they have human operators that remotely drive the vehicle in scenarios where their automated system is confused.

Which I assert is semantically equivalent to saying: Human drivers (even when operating at the diminished capacity of not even being present in the car) are less likely to make errors driving a car than AIs.

Re: AI coding is gambling

#112

Post by sidrag22 »

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.

exactly where my mind went as well. There aren't really levels to pulling a lever on a slot machine, other than the ability for each pull to result in more "plays" of the same potential outcome.

The reason i think this metaphor keeps popping up, is because of how easy it is to just hit a wall and constantly prompt "its not working please fix it" and sometimes that will actually result in a positive outcome. So you can choose to gamble very easily, and receive the gambling feedback very quickly unlike with an intern where the feedback loop is considerably delayed, and the delayed interns output might simply be them screaming that they don't understand.

Re: AI coding is gambling

#113

Post by dwa3592 »

Planktonne wrote: post #42
dwa3592 wrote: post #16

few thoughts on this- it's not gambling if the most expected outcome actually occurs. It also depends on what you're coding with; - If you're coding with opus4.6, then it's not gambling for a while. - If you'r coding with gemini3-flash, then yeah. One thing I have noticed though is- you have to spend a lot of tokens to keep the error/hallucination rate low as your codebase increases in size. The math of this problem…

> it's not gambling if the most expected outcome actually occurs. > you have to spend a lot of tokens to keep the error/hallucination rate low Ironically, I find your comment more effective at convincing me AI coding is gambling than the original article. You're talking about it the exact same way that gamblers do about their games.

so your whole argument is that you are convinced that ai coding is gambling because according to you i am talking about it like gamblers talk about gambling?

- Was there anymore intelligence that you wanted to add to your argument?

Re: AI coding is gambling

#114

Post by bensyverson »

deepfriedrice wrote: post #103
bensyverson wrote: post #22

Earlier quoted context omitted.

And that's why poker is a poor metaphor for agentic coding.

It's the perfect metaphor? Playing correctly/optimally is +EV. But nobody starts there, and many people don't ever get there. The main difference is that you're exploiting your own weaknesses, rather than others'. Limitations in typing speed, information gathering, pattern recognition.

In that case, couldn't you substitute painting, horseback riding or knitting? Nothing about poker has anything to do with agentic coding except "it's something you can learn."

Re: AI coding is gambling

#115

Post by bluefirebrand »

rustyhancock wrote: post #23

Life is full of variable reward schemes. Probably why we evolved to be so enamoured by them. Sometimes I think we put the Carr before the horse. We gamble because evolution promotes that approach. Yes I could go for the reliable option. But taking a punt is worth a shot if the cost is low. The cost of AI is low. What is a problem is people getting wrapped up in just one more pull of the slot machine handle. I use AI…

> The cost of AI is low

If we're only talking about money spent on prompting AI, maybe. The damage to online trust is massive imo. So is the damage done by looting the commons to build them.

Typical privatize the profits socialize the costs bullshit

Re: AI coding is gambling

#116

Post by dminik »

dwa3592 wrote: post #43
Planktonne wrote: post #42

Earlier quoted context omitted.

> it's not gambling if the most expected outcome actually occurs. > you have to spend a lot of tokens to keep the error/hallucination rate low Ironically, I find your comment more effective at convincing me AI coding is gambling than the original article. You're talking about it the exact same way that gamblers do about their games.

lol that's interesting. care to explain why?

I mean, the most expected outcome does mostly happen. When gambling, you are expected to lose money and you do. I'm not quite convinced that the same isn't true for vibecoding.

Re: AI coding is gambling

#117

Post by nickjj »

seanmcdirmid wrote: post #100
nickjj wrote: post #91

Earlier quoted context omitted.

> 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 ju…

I do everything manually. Prompt, look at the code, see if it works (copy / paste) and if it works but it's written poorly I'll re-prompt to make the code more readable, often ending with me making it more readable without extra prompts. Btw, this isn't about code formatting or linting. It's about how the logic is written.

> 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.

If it knows how to make the code more readable and / or better for performance by me simply asking "can you make this more readable and performant?" then it should be able to provide this result from the beginning. If not, we're admitting it's providing an initial worse result for unknown reasons. Maybe it's to make you as the operator feel more important (yay I'm providing feedback), or maybe it's to extract the most amount of money it can since each prompt evaluates back to a dollar amount. With the amount of data they have I'm sure they can assess just how many times folks will pay for the "make it better" loop.

Re: AI coding is gambling

#119

Post by samschooler »

parliament32 wrote: post #24
samschooler wrote: post #6

I think there are levels to this. - One shot or "spray and pray" prompt only vibe coding: gambling. - Spec driven TDD AI vibe coding: more akin to poker. - Normal coding (maybe with tab auto complete): eating veggies/work. Notably though gambling has the massive downside of losing your entire life and life savings. Being in the "vibe coding" bucket's worse case is being insufferable to your friends and family, wastin…

You remind me of those guys who swear they have a "system" at the casino.

I'm not saying I have a system. I'm saying there are levels to this stuff. It's not a binary "gambling" or "not gambling".

Re: AI coding is gambling

#120

Post by PaulHoule »

I think somebody like Nate Silver might say “everything is gambling” if you really pressed them.

A big theme of software development for me has been finishing things other people couldn’t finish and the key to that is “control variance and the mean will take care of itself”

Alternately the junior dev thinks he has a mean of 5 min but the variance is really 5 weeks. The senior dev has mean of 5 hours and a variance of 5 hours.

Post reply on HN