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

Perverse incentives of vibe coding

fredbenenson.medium.com

Post reply on HN
Print view View original

71–80 of 239 posts

Re: Perverse incentives of vibe coding

#71

Post by nkrisc »

0cf8612b2e1e wrote: post #64
GuinansEyebrows wrote: post #33

Earlier quoted context omitted.

i think at least a lot of things (if not most things) that i pay for have an agreed-upon result in exchange for payment, and a mitigation system that'll help me get what i paid for in the event that something else prevents that from happening. if you pay for something and you don't know what you're going to get, and you have to keep paying for it in the hopes that you get what you want out of it... that sounds a lot…

If I ask an artist to draw a picture, I still have to pay for the service, even if I am unhappy without the result.

Sounds like you should negotiate a better contract next time, such as one that allows for revisions.

Re: Perverse incentives of vibe coding

#72

Post by johnea »

I generally agree with the concerns of this article, and wonder about the theory of the LLM having a innate inclination to generate bloated code.

Even in this article though, I feel like there is a lot of anthropomorphization of LLMs.

> LLMs and their limitations when reasoning about abstract logic problems

As I understand them, LLMs don't "reason" about anything. It's purely a statistical sequencing of words (or other tokens) as determined by the training set and the prompt. Please correct me if I'm wrong.

Also, regarding this theory that the models may be biased to produce bloated code: I've reposted this once already, and no one has replied yet, and I still wonder:

----------

To me, this represents one of the most serious issues with LLM tools: the opacity of the model itself. The code (if provided) can be audited for issues, but the model, even if examined, is an opaque statistical amalgamation of everything it was trained on.

There is no way (that I've read of) for identifying biases, or intentional manipulations of the model that would cause the tool to yield certain intended results.

There are examples of DeepState generating results that refuse to acknowledge Tienanmen square, etc. These serve as examples of how the generated output can intentionally be biased, without the ability to readily predict this general class of bias by analyzing the model data.

----------

I'm still looking for confirmation or denial on both of these questions...

Re: Perverse incentives of vibe coding

#73

Post by Suppafly »

vanschelven wrote: post #14

> Its “almost there” quality — the feeling we’re just one prompt away from the perfect solution — is what makes it so addicting. Vibe coding operates on the principle of variable-ratio reinforcement, a powerful form of operant conditioning where rewards come unpredictably. Unlike fixed rewards, this intermittent success pattern (“the code works! it’s brilliant! it just broke! wtf!”), triggers stronger dopamine respon…

>Trying to get Image Generators to do what I want has a very "gambling-like" quality to it.

Especially when you try to get them to generate something they explicitly tell you they won't, like nudity. It feels akin to hacking.

Re: Perverse incentives of vibe coding

#74

Post by Suppafly »

nkrisc wrote: post #70
rapind wrote: post #67

Earlier quoted context omitted.

By this logic: - I buy stock that doesn't perform how I expected. - I hire someone to produce art. - I pay a lawyer to represent me in court. - I pay a registration fee to play a sport expecting to win. - I buy a gift for someone expecting friendship. Are all gambas. You aren't paying for the result (the win), you are paying for the service that may produce the desired result, and in some cases one of may possibly de…

None of those are a games of chance, except the first.

>None of those are a games of chance, except the first.

Neither is GenAI, the grandparent comment is dumb.

Re: Perverse incentives of vibe coding

#75

Post by sherburt3 »

Really makes you wonder where this is all going. What is going to be the thing where we say "Maybe we took this a little too far." I'm sure whatever bloated react apps we see today are nothing in comparison to the monstrosities we have in store for us in the future.

Re: Perverse incentives of vibe coding

#77

Post by abletonlive »

dingnuts wrote: post #17
vanschelven wrote: post #14

> Its “almost there” quality — the feeling we’re just one prompt away from the perfect solution — is what makes it so addicting. Vibe coding operates on the principle of variable-ratio reinforcement, a powerful form of operant conditioning where rewards come unpredictably. Unlike fixed rewards, this intermittent success pattern (“the code works! it’s brilliant! it just broke! wtf!”), triggers stronger dopamine respon…

it's not like gambling, it is gambling. you exchange dollars for chips (tokens -- some casinos even call the chips tokens) and insert it into the machine in exchange for the chance of a prize. if it doesn't work the first time you pull the lever, it might the second time, and it might not. Either way, the house wins. It should be regulated as gambling, because it is. There's no metaphor, the only difference from a sl…

Yikes. The reactionary reach for more regulation from a certain group is just so tiresome. This is the real mind virus that I wish would be contained in Europe.

I almost can't believe this idea is being seriously considered by anybody. By that logic buying any CPU is gambling because it's not deterministic how far you can overclock it.

Just so you know, not every llm use case requires paying for tokens. You can even run a local LLM and use cline w/ it for all your coding needs. Pull that slot machine lever as many times as you like without spending a dollar.

Re: Perverse incentives of vibe coding

#78

Post by AlexCoventry »

mnky9800n wrote: post #6
comex wrote: post #2

> There was no standardization of parts in the probe. Two widgets intended to do almost the same job could be subtly different or wildly different. Braces and mountings seemed hand carved. The probe was as much a sculpture as a machine. > Blaine read that, shook his head, and called Sally. Presently she joined him in his cabin. > “Yes, I wrote that," she said. "It seems to be true. Every nut and bolt in that probe wa…

That book is very much fun and also I never understood why Larry Niven is so obsessed with techno feudalism and gender roles. I think this is my favourite book but I think his best book is maybe Ringworld.

The zero-sum mentality which leads people to think that way is already clear in The Mote In God's Eye. I think the point of the book is that despite being superior to humans in every way imaginable, the Moties are condemned to repeated violent conflict by Malthusian pressures, because they have nowhere to expand. One way I interpret the "mote" in God's eye is the authors' belief that no matter how good we get, we'll always be in potentially violent conflict with each other for limited resources. (The "beam" in our own eye is then that we're still fighting each other over less pressing concerns. :-)

Re: Perverse incentives of vibe coding

#79

Post by Suppafly »

GuinansEyebrows wrote: post #28
princealiiiii wrote: post #19

Earlier quoted context omitted.

> It should be regulated as gambling, because it is. That's wild. Anything with non-deterministic output will have this.

maybe more accurately anything with non-deterministic output that you have to pay-per-use instead of paying by outcome.

>that you have to pay-per-use instead of paying by outcome.

That's still not gambling and it's silly to pretend it is. It feels like gambling but that's it.

Re: Perverse incentives of vibe coding

#80

Post by PaulDavisThe1st »

NathanKP wrote: post #49
dingnuts wrote: post #17

Earlier quoted context omitted.

it's not like gambling, it is gambling. you exchange dollars for chips (tokens -- some casinos even call the chips tokens) and insert it into the machine in exchange for the chance of a prize. if it doesn't work the first time you pull the lever, it might the second time, and it might not. Either way, the house wins. It should be regulated as gambling, because it is. There's no metaphor, the only difference from a sl…

This only makes sense if you have an all or nothing concept of the value of output from AI. Every prompt and answer is contributing value toward your progress toward the final solution, even if that value is just narrowing the latent space of potential outputs by keeping track of failed paths in the context window, so that it can avoid that path in a future answer after you provide followup feedback. The vast majorit…

This assumes you can easily and reliably identify the 10% you need to fix.
Post reply on HN