alt Hacker NewsUnless you're systematically repeating the exact same task, the most parsimonious explanation is that you're seeing natural variation based on different tasks, random sampling of tokens, etc.
Unless you're systematically repeating the exact same task, the most parsimonious explanation is that you're seeing natural variation based on different tasks, random sampling of tokens, etc.
I don't think this explains the phenomenon as is more temporal in nature - not prompt to prompt. I'm sure the AI labs gracefully degrade to simpler models when resources are low - why wouldn't they?