logoalt Hacker News

__natty__yesterday at 8:09 PM2 repliesview on HN

You compare tiny modal for local inference vs propertiary, expensive frontier model. It would be more fair to compare against similar priced model or tiny frontier models like haiku, flash or gpt nano.


Replies

javawizardyesterday at 8:21 PM

Not when the article they're commenting on was doing literally exactly the same thing.

ericdyesterday at 8:11 PM

Eh it’s important perspective, lest someone start thinking they can drop $5k on a laptop and be free of Anthropic/OpenAI. Expensive lesson.