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

> As long as you trust the government…

You should never trust the government


How is the smart sleep mask called?


It looks like it’s written by a LLM


Guilty as charged. I used Antigravity to handle the refactoring and docs so I could stay focused on the CUDA and VRAM orchestration.


This isn’t a job interview, drop the corpo speak. What’s going on with Cuda and vram? We are all friends here.


Haha fair enough.The actual internals are basically just one big fight with VRAM. I'm using decord to dump frames straight into GPU memory so the CPU doesn't bottleneck the pipeline. From there, everything—scene detection, hsv transforms, action scoring—is vectorized in torch (mostly fp16 to avoid ooming). I also had to chunk the audio stft/flux math because long files were just eating the card alive. The tts model stays cached as a singleton so it's snappy after the first run, and I'm manually tracking 'Allocated vs Reserved' memory to keep it from choking. Still plenty of refinement left on the roadmap, but it's a fun weekend project to mess around with.


Nice! Thanks :) what is ooming?


Out Of Memory-ing.


Great until Claude decides to delete your storage and all your containers are gone


‚ A secure, optional digital ID could be useful.‘ but never in the hands of a state.


Very good point


Love it


How does it compare to to Zig ?



Awesome


I love it so much. I always wanted to get started with hardware hacking , and this is the right place to start !


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

Search: