Goodfire
@GoodfireAI
Models usually know when they’re doing something wrong.
Probes let us “read their minds” to detect offensive cyber intent, reward hacking, strategic deception, and more. If you build or serve models, they’re your first line of defense.
Our latest post explains how they work &
Probes let us “read their minds” to detect offensive cyber intent, reward hacking, strategic deception, and more. If you build or serve models, they’re your first line of defense.
Our latest post explains how they work &
0:13 7 365