Our proposed exercises would provide evidence, not confident safety assurance or formal oversight.
We also encourage developers to work with other external groups to complement these efforts, and to unilaterally share evidence with the public.
METR says its proposed exercises would provide evidence, not confident safety assurance or formal oversight. It encourages developers to work with other external groups and to share evidence with the public unilaterally.
Part of a thread · earlier post
Our proposed exercises would provide evidence, not confident safety assurance or formal oversight.
We also encourage developers to work with other external groups to complement these efforts, and to unilaterally share evidence with the public.
Source: METR · x.comPublished · added here