Hacker Newsnew | past | comments | ask | show | jobs | submit | aligajani's commentslogin

There was a tool like this 5 years ago on [Github](https://github.com/emilwallner/Screenshot-to-code) that did similar thing using neural networks.


What you have made isn't a real product in my honest opinion, so it is understandable why you feel this way. You need to make it better and I think you have a chance.


How do you prevent SQL injections or bad queries?


we only execute SELECT statements and the user we connect with has readonly access.

On "bad queries", we rely heavily on the users past SQL history to understand correct JOIN's and how they normally define metrics / use the database in general.


Nice tool, will check it out. I had to go through a painstaking trial and error process to generate valid and deterministic JSON for my AI presentation tool called Slide Genie (https://slidegenie.vercel.app/). The hard part was making it work when temperature > 0.


The hype is real.


Oh no, not again..


Wow, this is great.


Al right, where do we get it?


Valid point


This is amazing.


Yes, this was my observation, but I see a pattern with the modern engineering workflow. It's convoluted. What could be done with basic npm scripts is now Webpack, so another abstraction that the beginners have to smash their head against, all in the pursuit of making a basic todo app. Not lying, I use these tools myself, but I try to survey a technology before using it. I ask myself the questions a) is it stable, by looking at any major GH issues and b) can I do it better natively and do away with using a library.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: