Large Language Model Performance Doubles Every 7 Months

https://lemmy.eco.br/post/14624591

Large Language Model Performance Doubles Every 7 Months - Brasil

By 2030, AI will greatly outperform humans in some complex intellectual tasks. Discover how LLMs are doubling their capabilities every seven months.

How is completely fucking up literally 50% of the time outperforming exactly???
It’s outperforming “messier” problems with a much lower success rate.