Hacker News: fabhed

New comment by fabhed in "Lovable incident report: Recovering from being taken down by GitHub"

fabhed — Thu, 09 Jan 2025 14:52:02 +0000

regardless of scale there will most likely be code paths where performance is not prioritized, and unexpected use-cases can put the stability at risk. In this case that was creating new repos. I believe if we only made a crazy amount of commits there would have been no issue.

New comment by fabhed in "Show HN: Claude Artifacts but creating real web apps"

fabhed — Thu, 29 Aug 2024 07:24:58 +0000

We use a dedicated firecracker VM for each project with a rust binary wrapping a vite dev server.

New comment by fabhed in "Ask HN: Who is hiring? (March 2024)"

fabhed — Thu, 14 Mar 2024 10:17:23 +0000

gptengineer.app / Lovable | ONSITE+HYBRID | Stockholm / London | Full-Time | Founding Engineers, Founding Designer

Lovable is made up of a team of pragmatic previous (YC) founders and CTOs, set on being the first to make autonomous code generation work.

This is a hard problem. We believe we can do it by selecting a limited domain, a great AI driven UX and crucially - carefully selecting a single 'AI-first' tech stack of open-source, that us engineers love to maintain. That we optimise the system of fine-tuned LLMs (+LMMs) to do well in.

We believe that rapid experimentation and hiring the brightest and most ambitious minds is the way we make this work. You'd be one of the first employees and have a big impact in shaping our product and company!

In particular we're looking for a Founding Engineer to join our team of AI and product engineers building the software that builds other software.

New comment by fabhed in "Show HN: Create and deploy multi-page web app prototypes using chat"

fabhed — Sat, 23 Dec 2023 10:03:59 +0000

Web apps that require more logic/interactivity than what is doable in traditional no-code editors

Show HN: Create and deploy multi-page web app prototypes using chat

fabhed — Fri, 22 Dec 2023 17:58:23 +0000

gptengineer.app lets you prototype, deploy and iterate on web apps using plain english. Here is a video of how I use it: https://www.loom.com/share/abda1d8e33134d0e944297afd3a51664

We designed it around the principles:

1. Leverage LLMs where they work best: LLMs are faster than humans at putting together prototypes of a few hundred lines of code. By using them early on, and give high level change request commands when the project is small, and then let human devs take over, it’s a productivity boost.

2. non-technical + programmer collaboration: All changes from the app is made as git commits, so that non-technical people (via chat) and programmers are able to contribute to the same code.

LLMs are expensive, but we left it open over the christmas holidays for anyone to try it out: https://run.gptengineer.app/

Would love to hear what you think!

Comments URL: https://news.ycombinator.com/item?id=38736710

Points: 17

# Comments: 14