Show HN: I made an AI Software Engineer with Claude 3 Opus | Hacker News Reader

Show HN: I made an AI Software Engineer with Claude 3 Opus

saas-quick.com

3 pointsgr00ve10 comments

Hey HN!

Andrej Karpathy, founding member of OpenAI and former Director of AI at Tesla, recently shared his thoughts on the future of programming:

The hottest new programming language is English

— Andrej Karpathy (@karpathy) January 24, 2023 https://twitter.com/karpathy/status/1617979122625712128?lang...

I've been using LLMs to help with my software engineering work since ChatGPT originally came out.

When Anthropic released their Claude 3 series models, I was shocked at the code quality they produce and was able to get new projects running with minimal debugging.

I've been listening a lot of the big interviews from Dwarkesh with people like Demis Hassabis and some of the technical discussion around task execution gave me the inspiration to attempt creating a full AI Software Engineering system requiring only a text prompt.

It's not accurate enough to programmatically deploy, but seeing what the system can produce in 30mins-1hr has continually blown me away.

Unlike Devin, which is still in a 'waitlist period', saas-quick is available to use right now.

I'm a solo developer and the frontend isn't polished or anything, but you can follow along the process as each task is executed and download the project zip at the end.

I appreciate your time and am grateful for any feedback!

Desperately needs some examples of what it created or even a demo (maybe show the resulting app, and one file, pay for full repo). Need some signal this is worth it.

I'm kind of shocked at how little substance there is here and then immediately I'm asked if I want to pay $29 and get started with whatever this is.

Do you have questions about these statements?

"Key Features Cutting-edge repository generation powered by Claude 3 Flat rate fee for each project generation Generates highly functional code that serves as a robust starting point Minimal debugging required to deploy the generated code"

"Our advanced AI technology creates highly functional repositories that serve as a solid foundation for your projects".

I agree if there was a demo video it would clear up a lot of confusion. Or maybe screenshots/feature details on the landing page would help. The project page has an input box to describe your project, it writes all the files for the project, and then shows a download button for the zip. All projects are containerized with Docker and have configs that you'd want in a production deployment environment.

I think they have the M and V but not quite the P. P is proposition. Just needs a bit more info as to what to expect, some examples and perhaps social proof.

Can you add a GitHub repo with sample generated projects? Even maybe several

I am just from checking the site. I would appreciate a demo video to help visitors gain a deeper understanding of how the AI SE works

Got it! I have been trying to think of creative ways to show a demo video when it takes 30 min to an hour. I might try to a few timelapse/speedrun type clips for commonly cloned projects (like a Notion Clone). Thanks for the feedback

I was on the site and I can't see any demos at all. No one's gonna drop $29 on this without knowing what it does

Understandable! I will work on some demo videos this weekend :)

Reply on news.ycombinator.com