I don't ever want to be dependent on a cloud service to be productive, and I don... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jckahn 4 months ago \| parent \| context \| favorite \| on: Ask HN: Who uses open LLMs and coding assistants l... I don't ever want to be dependent on a cloud service to be productive, and I don't want to have to pay money to experiment with code. Paying money for probabilistically generated tokens is effectively gambling. I don't like to gamble.

nprateem 4 months ago [–]

Where did you get your free GPU from?

nicce 4 months ago | | [–]

The problem is the same as owning the house vs. renting.

jckahn 4 months ago | | | [–]

I just use my AMD Framework 13 and 24GB M4 Mac mini. They run gpt-oss models, but only the 20b fits on the mini.

serf 4 months ago | | [–]

GPUs can do other things. Cloud service LLM providers cannot.

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