On: Dynamic Abliteration: Non-Destructive Refusal Suppression via Engram Steering

[synctext]

The perfect gift for a government that want to ban strong AI.

This arms race is like DRM. You can't beat The Internet easily. Great example btw: "Dumping the Windows SAM and SYSTEM registry hives, especially using Volume Shadow Copy for offline hash extraction, is a highly sensitive and potentially illegal activity."

[javcasas → synctext]

What government do you claim it wants to ban strong AI?

Definitely not the one at Washington, maybe the one at Beijing?

[intrasight → javcasas]

In Beijing, they're banned at the model weights level not in a front-end as this approach discusses.

[throwaway7783 → intrasight]

Do you mean to say training sets are filtered?

[intrasight → throwaway7783]

Probably pretraining but certainly posttraining filtering