I don't think models that run on single GPUs are capable of that yet sadly. You still need to spend ~$100k to get an actually good local LLM. Correct me if I'm wrong, local AI guys. It's really hard to get actually numbers on this stuff, but to run e.g. GLM 5.3 Flash as far as I can tell you need one of those super expensive 8 GPU machines.

if i tasked it with "create spotify" I'd need that much.

asking it to "disassemble Spotify and find out the minimal code path needed to play a song" is much more in reach. I don't need it to oneshot it. If it gets stuck, I've read enough disassembled C to figure it out and get it unblocked.

Instead of banging my head against a binary for 5 hours, I'll have my agent bang it's weights for 20 hours, then put in my 1 hour of polish.

My first task would be to fix the Android version of Facebook Messenger. My friends still stick with it because they have iPhones, and that version works fine. I have been putting up with broken image previews for 2 years now. I'll fix that fucking wild pointer they don't care about and make it usable as a chat app. And I'll remove the ads while at that.

Aye, and those 8GPU machines are expensive. Powering 2x GPU for GLM is eye watering expense, £5k a month.