Skip to content
Read the original: Goodfire· Published 38/100AI score38/100

Goodfire's method catches more unsafe biology requests with fewer false positives

Original titleCompared to frontier model safeguards, our method catches more unsafe biological requests while dramatically reducing false positives (se...

AISummary

Goodfire reports that its method catches more unsafe biological requests than frontier model safeguards while dramatically reducing false positives. The claim is illustrated by a plot in the first tweet of the thread.

Read the original x.com

Source: Goodfire · x.comPublished · added here