alt Hacker NewsNot disputing the increase in quality, just stating that non-cherry-picked benchmarks show it is more verbose at Max effort
Replies
93po • today at 6:21 PM
Is verboseness the only measure of token efficiency towards overall task completion?
Not disputing the increase in quality, just stating that non-cherry-picked benchmarks show it is more verbose at Max effort
Is verboseness the only measure of token efficiency towards overall task completion?
so don't use it at max? The benchmarks suggest that high/xhigh are more than sufficient to be ahead and a whole magnitude below max with regards to token usage. I'd treat that as an outlier and not how verbose the model is in general (QED I know)