Lovable | Stockholm (In-person) | Full-Stack, Design, and ML eng
We sponsor visas and have very generous relocation packages (even if you just want to come for a year).
Lovable is building an AI software engineer that lives in your browser. Building excellent software engineering agents is significantly harder than people think. We need the best engineers in the world to join us and will compensate you accordingly.
One thing that seemingly is missing is the ability to tag a specific error with an error code. You typically want to know that all of a sudden the ”failed to get user” error is being returned a lot. Since the message is a dynamic string you can’t just group by the string so unless you build it as part of your abstraction it becomes very hard to do.
Edit: looking more carefully at the lib I assume that ”tag” is the concept that is supposed to cover this?
Yeah you shouldn't have to add stuff to the .env file. If you setup Supabase any secrets should be added to the edge functions as env vars. Here's an example where it prompted me to add the RESEND_API_KEY to the Supabase Edge function secret: https://lovable.dev/projects/e66eacea-f46f-473c-aa6b-6a90da4...
Great questions! There are several LLM calls behind a single prompt that you submit and we do dynamically assemble the prompt to the AI based on what you're asking for. But we do generate most files at once.
1) We use whichever LLM that is performing best at the time, so no, not necessarily OpenAI
2) Only images as attachments for now. You can add more files by uploading them to the connected Github repo.
Will try it out. Regardless of if I’ll use it or not I think this project is a great example of the rare type of engineering craft that seems to be a pre-requisite to build truly great software. A great signal if I were hiring.
Curious to know how to which degree they are self hosting, seems they'll buy their own servers but I doubt they'll go all the way to buying land and building their own data centers?
Having been at a Clojure startup I can second this, despite our non existent brand we found great candidates. And teaching a smart junior developer Clojure wasn't harder than teaching people Ruby or Java. As soon as the initial lisp shock is over learning is much faster due to the simplicity (it's just data).
My understanding is that Stripe billing can be managed completely no-code from the Stripe dashboard? And I think it includes automatic tax, prorations etc.
The fact that Apple's developer tooling is described as great makes me suspicious if the author has used JS tooling in a serious way. VS Code is just so much better than XCode. My experience developing native apps in SwiftUI is also that the documentation is very very lacking. And lastly I wasn't able to get a hover effect without dropping tons of frames. My lack of experience I'm sure is partly to blame for the app's poor performance, but it certainly wasn't performant out of the box. React would have been significantly more performant for my use case.
This is a sub theme in the book "Subprime attention crisis" that more broadly argues that the fact that programmatic advertising is based on similar mechanics as financial systems also means it's vulnerable to bubbles in the same way. Interesting read but I would have loved some more data on the actual efficacy of programmatic advertising.