News for hackers. Stuff that matters.

jmilldotdev

Re:Building SafeDate: Help Us Make Dating Apps Safer for Women on Wednesday August 06, 2025 @09:01AM (#44811390)
> Any tips on building trust or avoiding pitfalls?

Check your firebase security rules, then check them again

Re:Midlibrary: Library of 4000 Midjourney artistic styles on Sunday January 14, 2024 @01:30PM (#38992988)
Not necessarily. Both of us (the creators) enjoy using AI in our free time to make images and creating and curating aesthetically pleasing images.

It was not used purely to cut costs.

Re:Midlibrary: Library of 4000 Midjourney artistic styles on Saturday January 13, 2024 @02:40PM (#38983723)
We’re going to get a first run printed at the start of March. Ship would probably be April-May. Doing some final content polishing and playtesting before then.

You can sign up here if you want updates! https://bcad.substack.com/

Re:Midlibrary: Library of 4000 Midjourney artistic styles on Saturday January 13, 2024 @11:17AM (#38981316)
https://www.bcad.one/project/7

we produced a connection card game in a couple of months end-to-end using AI. text is a true mixture of our ideas and GPT's 'ideas'. we gave GPT the vibe we wanted, let it generate tons of new stuff, then we heavily curated and remixed it.

art is created and curated by various AI tools. it does not rely on any particular artist's style. we bootstrapped the game using our own money, and this was only possible because we were able to produce our own visual assets.

AI is a tool in our kit just like figma and photoshop. people consistently have fun with the game in our playtest, and we're bringing our first print run to the world soon.

Show HN: A GPT-4V bot that creates captchas for humans

https://www.bcad.one/project/8

Hey HN,We built a GPT-4V powered Discord bot that creates captchas for humans using mobile game screenshots.The bot receives a random mobile game screenshot as an input, then is instructed to:- Create a difficult, but not impossible puzzle based on information in the screenshot such as numbers, word lengths, etc - Solve the puzzle step by step, showing its justification for the solution -...

( Read More... | no comments | on HN )
Re:Langchain Is Pointless on Saturday July 08, 2023 @10:16PM (#36650865)

Show HN: Coke Diffusion, Native Advertising Powered Text-to-Image Twitter Bot

https://twitter.com/coke_diffusion/status/1629173900197371904

Playing with the horrid news of Bain x OpenAI x CocaCola partnership, we built a Twitter bot which makes coca-cola themed stable diffusion imagesDrop page: https://www.bcad.one/project/4Code: https://github.com/BeforeCutieAfterDoggo/coke-diffusion Code:

( Read More... | no comments | 3 points | on HN )
getting to the top of hackernews
Bugs-as-a-Service (BAAS)
our best defense against the robots is a good offense
Ah, good catch. Will fix.
Also, it's open source and all the prompts we use are in this file:

https://github.com/BeforeCutieAfterDoggo/spaghettify/blob/ma...

You can take these and play around with them in the OpenAI playground as well.

There have been many moments in building this thing where I expected something terrible and got something that actually looked better than what I had.
That's a really good one. Like the 'introduce bug' one, but just the comments are factually incorrect.

Show HN: Spaghettify – A VSCode Extension to make your code worse with AI

https://www.spaghettify.dev/

Recently, I saw Github Next Code Brushes (https://githubnext.com/projects/code-brushes) which is a VSCode extension that can use AI to do things like make your code more readable, add types, etc.This inspired me: what if there was an extension that could use AI to make your code worse as well?Meet Spaghettify. An extension I developed that can do things like:- Obscure your code- Introduce a...

( Read More... | 66 comments | 5 points | on HN )