> 99% more efficient every 3 years
It's 2x efficiency. Then I'd take 50% less power instead of ridiculous 99% less power.
GPT-4 came out 3 years ago and you can run comparable models for 1% of the cost nowadays. That is not 2x efficiency. That's two orders of magnitude in end-to-end compute efficiency.
alt Hacker News
GPT-4 came out 3 years ago and you can run comparable models for 1% of the cost nowadays. That is not 2x efficiency. That's two orders of magnitude in end-to-end compute efficiency.