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

111–120 of 239 posts

Re: Perverse incentives of vibe coding

#111

Post by ramoz »

mecredis wrote: post #100
ramoz wrote: post #96

I disagree with the idea that LLM providers are deliberately designing solutions to consume more tokens. We're in the early days of agentic coding, and the landscape is intensely competitive. Providers are focused on building highly capable systems to drive adoption, especially with open-source alternatives just a git clone away. Yes, Claude Code can be token-heavy, but that's often a trade-off for their current leve…

Hi! Author here. I don't actually think they're deliberately doing this, hence my choice of "perverse incentives" vs. something more accusatory. The issue is that they don't have a ton of incentive to fix it. Agree with you on all the rest, and I think writing a post like this was very much intended as a gut-check on things since the early days are hopefully the times when things can get fixed up.

My speculation is that these companies have significant reason to prioritize lowering the amount of tokens produced as well as cost of tokens.

The leaked Claude Code codebase was riddled with "concise", "do not add comments", "mimic codestyle", even an explicit "You should minimize output tokens as much as possible" etc. Btw, Claude Code uses a custom system prompt, not the leaked 24k claude.ai one.

Re: Perverse incentives of vibe coding

#112

Post by hx8 »

brooke2k wrote: post #98

I don't understand the productivity that people get out of these AI tools. I've tried it and I just can't get anything remotely worthwhile unless it's something very simple or something completely new being built from the ground up. Like sure, I can ask claude to give me the barebones of a web service that does some simple task. Or a webpage with some information on it. But any time I've tried to get AI services to h…

Probably 80% of the time I spend coding, I'm inside a code file I haven't read in the last month. If I need to spend more than 30 seconds reading a section of code before I understand it, I'll ask AI to explain it to me. Usually, it does a good job of explaining code at a level of complexity that would take me 1-15 minutes to understand, but does a poor job of answering more complex questions or at understanding more complex code.

It's a moderately useful tool for me. I suspect the people that get the most use out of are those that would take more than 1 hour to read code I would take 10 minutes to read. Which is to say the least experienced people get the most value.

Re: Perverse incentives of vibe coding

#113

Post by lukan »

brooke2k wrote: post #98

I don't understand the productivity that people get out of these AI tools. I've tried it and I just can't get anything remotely worthwhile unless it's something very simple or something completely new being built from the ground up. Like sure, I can ask claude to give me the barebones of a web service that does some simple task. Or a webpage with some information on it. But any time I've tried to get AI services to h…

Yesterday I gave cursor a try and made my first (intentionally very lazy) vibe coding approach (a simple threejs project). It accepted the task and did things, failed, did things, failed, did things ... failed for good.

I guess I could work on the magic incantations to tweak here and there a bit until it works and I guess that's the way it is done. But I wasn't hooked.

I do get value out of LLM's for isolated broken down subtasks, where asking a LLM is quicker than googling.

For me, AI will probably become really usefull, once I can scan and integrate my own complex codebase so it gives me solutions that work there and not hallucinate API points or jump between incompatible libary versions (my main issue).

Re: Perverse incentives of vibe coding

#114

Post by cogman10 »

0cf8612b2e1e wrote: post #106
cogman10 wrote: post #92

Earlier quoted context omitted.

In the US? No, you actually do not need to pay for the service if you deem the quality of the output to be substandard. In particular with art, it's pretty standard to put in a non-refundable downpayment with the final payment due on delivery. You only lose those rights in the contracts you sign (which, in terms of GPT, you've likely clicked through a T&C which waves all right to dispute or reclaim payment). If you a…

There must be artists working on an hourly contract rate. Maybe art is special, but there are other professions where someone can invest heaps of time and effort without delivering the expected result. A trial attorney, treasure hunter, oil prospector, app developer. All require payment for hours of service, regardless of outcome.

It'll mostly depend on the contract you sign with these services and the state you live in.

When it comes to work that requires craftmanship it's pretty common to be able to not pay them if they do a poor job. It may cost you more than you paid them to fix their mistake, but you can generally reclaim your money you paid them if the work they did was egregiously poor.

Re: Perverse incentives of vibe coding

#115

Post by colechristensen »

brooke2k wrote: post #98

I don't understand the productivity that people get out of these AI tools. I've tried it and I just can't get anything remotely worthwhile unless it's something very simple or something completely new being built from the ground up. Like sure, I can ask claude to give me the barebones of a web service that does some simple task. Or a webpage with some information on it. But any time I've tried to get AI services to h…

Some people do really repetitive or really boilerplate things, others do not.

Also you have to learn to talk to it and how to ask it things.

Re: Perverse incentives of vibe coding

#116

Post by thimabi »

Workaccount2 wrote: post #4

Are using the APIs worth the extra cost vs using the web tools? I haven't used any API tools, I am not a programmer, but I have generated many millions of tokens in the web canvas, something that would cost way more than the $20 I spend for them.

I think the idea that LLMs are incentivized to write verbose code fails when one considers non-API usage.

Like you, I’ve accumulated tons of LLM usage via apps and web apps. I can actually see how the models are much more succinct there compared to the API interface.

My uneducated guess is that LLM models try to fit their responses into the “output tokens” limit, which is surely much lower in UIs than what can be set in pay-as-you-go interfaces.

Re: Perverse incentives of vibe coding

#117

Post by tippytippytango »

grufkork wrote: post #38
tippytippytango wrote: post #7

This article captures a lot of the problem. It’s often frustrating how it tries to work around really simple issues with complex workarounds that don’t work at all. I tell it the secret simple thing it’s missing and it gets it. It always makes me think, god help the vibe coders that can’t read code. I actually feel bad for them.

Working as an instructor for a project course for first-year university students, I have run in to this a couple of times. The code required for the project is pretty simple, but there are a couple of subtle details that can go wrong. Had one group today with bit shifts and other "advanced" operators everywhere, but the code was not working as expected. I asked them to just `Serial.println()` so they could check what…

Sounds like you found a good problem for the students. Having the experience of failing to get the right answer out of the tool and then succeeding on your whits creates an opportunity to learn these tools benefit from disciplined usage.

Re: Perverse incentives of vibe coding

#118

Post by jiggawatts »

erulabs wrote: post #85

These perverse incentives run at the heart of almost all Developer Software as a Service tooling. Using someone else's hosted model incentivizes increasing token usage, but it's nothing special about AI. Consider Database-as-a-service companies: They're not incentivized to optimize on CPU usage, they charge per cpu. They're not incentivized to improve disk compression, they charge for disk-usage. There are several DB…

My favourite example of this is the recent trend towards “wide events” replacing logs and metrics… spearheaded and popularised by companies that charge by the gigabytes ingested.

Re: Perverse incentives of vibe coding

#120

Post by rcxdude »

jerf wrote: post #16
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…

Yeah, I've had that thought too. I think a lot about Motie engineering versus human engineering. Could Motie engineering be practical? Is human engineering a fundamentally good idea, or is it just a reflection of our working memory of 7 +/- 2? Biology is Motie-esque, but it's pretty obvious we are nowhere near a technology level that could ever bring a biological system up from scratch. If Motie engineering is a good…

>I think a lot about Motie engineering versus human engineering. Could Motie engineering be practical? Is human engineering a fundamentally good idea, or is it just a reflection of our working memory of 7 +/- 2? Biology is Motie-esque, but it's pretty obvious we are nowhere near a technology level that could ever bring a biological system up from scratch.

It's the kind of thing you commonly get if you let an unconstrained optimization process run for long enough. It will generally be better, according to whatever function you're optimizing for. The main disadvantage, apart from being hard to understand or modify the design, is manufacturing and repair (needing to make many different parts), but if you have sufficiently good manufacturing technology (e.g. atomic level printers), then that may be a non-issue. And in software it's already feasible: you can see very small scale versions of this in extremely resource-constrained environments where it's worthwhile really trying to optimize things (see some demoscene entries), but it's pretty rare (some tricks that optimizing compilers pull off are similar, but they are generally very local).

Post reply on HN