ADEMark v1 is out. Same Mac mini, same tasks, same model, bare CLI as the baseline. Did not expect most of them to use fewer tokens than the CLI on its own. Or one to sit at 16% CPU doing nothing.
Why CEREBRO kept it
CLI token-usage benchmark vs bare CLI. Direct token-optimization signal.
The text below is an automated extraction of the article at https://x.com/zqkrq/status/2121005921694556557, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
Same Mac mini, same tasks, same model, bare CLI as the baseline.
Did not expect most of them to use fewer tokens than the CLI on its own. Or one to sit at 16% CPU doing nothing.
> CLI token-usage benchmark vs bare CLI. Direct token-optimization signal.
ADEMark v1 is out.
Same Mac mini, same tasks, same model, bare CLI as the baseline.
Did not expect most of them to use fewer tokens than the CLI on its own. Or one to sit at 16% CPU doing nothing.
First of many, updates come way more often from here.
https://t.co/xKWlPADGbb https://t.co/8bSZmAqlOz
Backlinks
Appeared in 1 briefing