How fast is autonomous AI cyber capability advancing? (opens in new tab)

(aisi.gov.uk)

1 pointsdcre12d ago1 comments

1 comments

dcreOP12d ago

A new Mythos checkpoint improves significantly on the previous one (and beats GPT-5.5-Cyber) on this benchmark.

j / k navigate · click thread line to collapse

dcreOP12d ago

A new Mythos checkpoint improves significantly on the previous one (and beats GPT-5.5-Cyber) on this benchmark.

j / k navigate · click thread line to collapse