allanrbo

Very cool! But you are not revealing what the $20 hardware is so others can build one too?

Like the days of Norton Commander

Almost the same. The neat trick here is to ask the model to reply with just 1 letter, which is one token, rather than a long string of json. Its quicker. And just the fact that Jev made a pretty decent API for structuring your questions. And they do the massive parallelization.

The technique i mentioned in the blogpost works with video too. I tested succesfully with Qwen/Qwen3-VL-8B-Instruct. Effecient caching is a little trickier though, but very doable.

Ah, will try, thanks!

Fondly remember Beej's Guide to Network Programming back in the day :-)

Does anyone actually like Docker Desktop? I much preferred Docker before it had weird UI parts to too. Have since switched to Podman.

I wish all shops just have a clear email address. Id much prefer emailing over placing a voice call...

Screenshot or bust

SIM=subscriber identity module. sim=simulator. :-)