zlacker

Perverse incentives of vibe coding

submitted by laurex+(OP) on 2025-05-14 19:29:38 | 207 points 228 comments
[view article] [source] [go to bottom]

NOTE: showing posts with links only show all posts
9. sigmai+w6[view] [source] 2025-05-14 20:16:35
>>laurex+(OP)
In section 4, the author writes "... cheaper than Claude 3.7 ($0.80 per token vs. $3)".

This is an obvious mistake, the price is per Megatoken, not per token.

Source: https://www.anthropic.com/pricing

16. biker1+a8[view] [source] 2025-05-14 20:27:57
>>laurex+(OP)
Can we please stop using 'vibe coding' to mean 'ai assisted coding'?? (best breakdown, imo: https://simonwillison.net/2025/Mar/19/vibe-coding/)

Is it really vibe coding if you are building a detailed coding plan, conducting "git-based experimentation with ruthless pruning", and essentially reviewing the code incrementally for correctness and conciseness? Sure, it's a process dependent on AI, but it's very far from nearly "forget[ing] that the code even exists".

That all said, I do think the article captures some of the current cost/quality dilemmas. I wouldn't jump to conclusions that these incentives are actually driving most current training decisions, but it's an interesting area to highlight.

◧◩
20. Animat+59[view] [source] [discussion] 2025-05-14 20:35:19
>>biker1+a8
"Vibe coding" is a trend.[1]

[1] https://trends.google.com/trends/explore?geo=US&q=%22vibe%20...

◧◩◪
49. ben_w+kd[view] [source] [discussion] 2025-05-14 20:58:16
>>martin+kb
Given that LLMs are trained on humans, who don't respond well to being dehumanised, I expect anthropomorphising them to be better than the opposite of that.

https://www.microsoft.com/en-us/worklab/why-using-a-polite-t...

55. neonat+2e[view] [source] 2025-05-14 21:02:24
>>laurex+(OP)
https://archive.ph/EzbNK
◧◩◪
63. fwip+1h[view] [source] [discussion] 2025-05-14 21:23:37
>>jerf+c7
For me, "Motie engineering" always brings to mind "The Story of Mel." http://www.catb.org/jargon/html/story-of-mel.html
112. rcarmo+ws[view] [source] 2025-05-14 23:01:04
>>laurex+(OP)
As it happens, I wrote about the need for planning and organizing work (for greenfield or understanding existing projects) only yesterday: https://taoofmac.com/space/blog/2025/05/13/2230
◧◩◪◨
171. kbaker+TN[view] [source] [discussion] 2025-05-15 02:59:47
>>__mhar+Yw
Try https://aider.chat + OpenRouter.ai, pay-as-you-go, use any model you want, I use Claude Sonnet.

It has a very good system prompt so the code is pretty good without a lot of fluff.

◧◩◪◨⬒⬓
175. guyfhu+OP[view] [source] [discussion] 2025-05-15 03:23:38
>>tptace+oB
This seems a self servingly literal interpretation of the op’s original comment.

Clearly something like “server telemetry” is the datacenter’s “CRUD app” analogue.

It’s a solved problem that largely requires rtfm and rote execution of well worn patterns in code structure.

Please stick to the comment guidelines:

> Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.

https://news.ycombinator.com/newsguidelines.html

◧◩◪◨⬒
196. jazoom+Kd1[view] [source] [discussion] 2025-05-15 08:31:22
>>AlexCo+vx
I created a script to pack it into a markdown file. Later I found this which does a better job, so I use it now.

https://github.com/yamadashy/repomix

[go to top]