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

$85,000 in tokens later: What I learned from scaling agentic coding at Lovable

lovable.dev

Post reply on HN
Print view View original

11–20 of 61 posts

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#11

Post by StrLght »

> During the first week of June I merged 293 PRs, and have found no production defects tracing back to those changes so far. The latter part is a bit of good luck — I think 2-3 minor and 1 major defect would be acceptable for this volume.

At this point, articles about LLMs paired with meaningless metrics have become a classic combo. I get that it's typical corporate BS, but publishing this widely is just weird. "Look, my productivity is skyrocketing according to a chart that only my manager cares about!"

Mitchell Hashimoto put it well: https://xcancel.com/mitchellh/status/2071971627748020409

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#12

Post by altmanaltman »

justinclift wrote: post #3

> Reviewing AI-written code line-by-line isn't practical or a good use of anyone's time. And the usual answer to problems created by the use of AI is to use more AI, so you switch to AI reviews by default. Ugh. Sure, for non-critical stuff that might be acceptable, but for anyone working on core banking or infrastructure PLEASE don't be doing this.

For critical stuff, there is already a ton of regulations in place that prevent this kind of thing from happening. Why do people think programmers working in such industries have no oversight and can ship whatever they want and however they want? It simply doesn't work that way in those industries.

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#13

Post by altmanaltman »

I had an idea for a video long time ago. The idea was to try building lovable using lovable and then building another lovable within that using it. They market to normal people as if anything is possible but its very disingenous to offer a no code platform with the type of marketing they do. They are not alone, selling people the dream of "just use this to make a million dollar app!" while they make money off them even if the app works out or not.

These platforms should do a revenue-share pricing where all these amazing apps created on the platform should only pay it if the app actually generates revenue if they really buy their marketing.

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#15

Post by tangenter »

StrLght wrote: post #11

> During the first week of June I merged 293 PRs, and have found no production defects tracing back to those changes so far. The latter part is a bit of good luck — I think 2-3 minor and 1 major defect would be acceptable for this volume. At this point, articles about LLMs paired with meaningless metrics have become a classic combo. I get that it's typical corporate BS, but publishing this widely is just weird. "Look…

“Spotify ships 4,500 production deploys a day” LMAO

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#16

Post by qmarchi »

kelseyfrog wrote: post #10
hoppp wrote: post #6

Earlier quoted context omitted.

Its fine for web and mobile as long as you can't get sued if data leaks or you get hacked.

Fortunately AI lawyers are much cheaper than real lawyers.

Except that any lawyer worth their salt won't touch AI for fear of getting disbarred.

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#17

Post by vivzkestrel »

- i swear to god it has been 3 years since LLMs came out

- i still have no idea what people are running for more than 5 mins

- if you are sitting and writing 20000 page requirement documents for your next project and having agentic AI agents create the whole damn project from scratch, you are doing it all wrong

- you ll end up eroding all your skills that translate requirements to code and worse you are dependent on these so called couple of frontier labs

- in about 5-10 years you are going to see absolutely horrible effects of this LLM stuff at scale when most engineers wont be able to write a script tag in html without an LLM

- mark my words

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#18

Post by jdjdkrjdjjdj »

vivzkestrel wrote: post #17

- i swear to god it has been 3 years since LLMs came out - i still have no idea what people are running for more than 5 mins - if you are sitting and writing 20000 page requirement documents for your next project and having agentic AI agents create the whole damn project from scratch, you are doing it all wrong - you ll end up eroding all your skills that translate requirements to code and worse you are dependent on…

[flagged]

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#19

Post by justinclift »

altmanaltman wrote: post #12
justinclift wrote: post #3

> Reviewing AI-written code line-by-line isn't practical or a good use of anyone's time. And the usual answer to problems created by the use of AI is to use more AI, so you switch to AI reviews by default. Ugh. Sure, for non-critical stuff that might be acceptable, but for anyone working on core banking or infrastructure PLEASE don't be doing this.

For critical stuff, there is already a ton of regulations in place that prevent this kind of thing from happening. Why do people think programmers working in such industries have no oversight and can ship whatever they want and however they want? It simply doesn't work that way in those industries.

> Why do people think programmers working in such industries have no oversight and can ship whatever they want and however they want?

I've worked in those industries, and there's a large gap between the theory of what you're saying vs the practical reality when the CxO suite are pushing AI on everyone. :(

Re: $85,000 in tokens later: What I learned from scaling agentic coding at Lovable

#20

Post by justinclift »

kelseyfrog wrote: post #10
hoppp wrote: post #6

Earlier quoted context omitted.

Its fine for web and mobile as long as you can't get sued if data leaks or you get hacked.

Fortunately AI lawyers are much cheaper than real lawyers.

For good reason. :)

This is a website collecting the AI mishaps in the law field around the world:

https://www.damiencharlotin.com/hallucinations/

It seems pretty extensive (1696 cases identified so far), and appears to be updated regularly. :)

Post reply on HN