Training models cost tens of millions, their revenues from sub + api are well above hundreds of millions.

If you look at minimax IPO data, you can see that they spent 3x their revenue on "cloud bills".

So yes, it's probable that they do subsidize inference through subscriptions in order to capture market.

No inferrence provider is profitable, and most run on VC money to serve customers.

2. Trained on opensource vs trained on copyright is a solid rationale. But yes, LLM have been trained on copyrighted code, as an UnrealEngine user, it's pretty obvious that any LLM has knowledge of the engine source code and patterns, not only the doc. But it might be marginal since the quantity of open source code is gigantic.

Retribution to copyright holders for artistic work would make a lot of sense. It reminds me the shift from emule/kazaa everything towards spotify. Legal streaming has almost totally replaced music pirating. And it looks beneficial for artists since we never had that much production in human history.

I don't believe in LLM replacing devs either, it increases my scope but not in any point allow me to prompt in the morning and collect the money on the evening. It's still a job of full focus, even if I'm braining less. I feel I moved to a managing position instead of a crafter. Pretty happy to leave the webdev world for gamedev since LLM are years away to handle complex abstracts and produce clean code.

From your feedback, GenAI makes obvious some important problems our society is facing. LLM result is technical, genAI result is emotional because despite being the same exact tools, one produces text and the other produces images.

I obviously see the rants of my own echo chamber, but the complaints about GenAI are mostly about copyright (as you said) but they also make it a moral stand. GameDev using GenAI are accused of being "lazy", of having no vision, etc... unquantifiable.

Your remark about aesthetic would map 1:1 to poor code quality. (LLM code quality can be pretty bad, depends on prompt like always).

"Stealing" is a word aften use to criticize genAI.

I have several agents runing in parallel, they require inputs every 1 to 5 minutes.

Im switching context all the time, and I must hold a larger context in my brain RAM instead of being focused on a single topic.

I'm not writing code anymore for web development.

On the other side, when doing game dev, with all the spatial geometry necessary, LLM are useless 97% of thr time.

Every AI CEO selling the disparition of developers in 6 months. But I don't see any developer complaining about LLM steeling our job, or that LLM are infringing copyright and are bad for humanity.

I can't possibly make a fundamental difference between GenAI and vibe coding, they are the same thing.

Comments URL: https://news.ycombinator.com/item?id=46022817

Points: 2

# Comments: 13

They had everything, money, talent, network and hype.

How can it lead to such a disaster?

Comments URL: https://news.ycombinator.com/item?id=44363225

Points: 7

# Comments: 4

What I do is to write pure functions with LLM. Once I designed the software and I have the API, I can tell the model to write a function which does a specific job where I know the inputs and outputs but I'm lazy to write the code itself.

I'm not fuding LLM, I use it everyday, all the time. But it won't make me a better engineer. And I deeply believe that becoming a good engineer helped me becoming a better human, because how the job make you face your own limits, train you to be humble and constantly learning.

Vibe coding won't lead to that same and sane mindset.

Lot of cool cpp to write

Second, not all IAP are abusive, I didn't said nor meant that.

https://dictionary.cambridge.org/dictionary/english/monetize