News for hackers. Stuff that matters.

A comment on Dynamic Abliteration: Non-Destructive Refusal Suppression via Engram Steering.

Re:Dynamic Abliteration: Non-Destructive Refusal Suppression... by synctext on Thursday September 24, 2026 @11:16AM (#49831791)
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."

[ Parent | on HN ]
Re:Dynamic Abliteration: Non-Destructive Refusal Suppression... by javcasas on Thursday September 24, 2026 @11:21AM (#49831882)
What government do you claim it wants to ban strong AI?

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

[ Parent | on HN ]
Re:Dynamic Abliteration: Non-Destructive Refusal Suppression... by intrasight on Thursday September 24, 2026 @11:24AM (#49831936)
In Beijing, they're banned at the model weights level not in a front-end as this approach discusses.
[ Parent | on HN ]
Re:Dynamic Abliteration: Non-Destructive Refusal Suppression... by throwaway7783 on Thursday September 24, 2026 @01:04PM (#49833605)
Do you mean to say training sets are filtered?
[ Parent | on HN ]
Re:Dynamic Abliteration: Non-Destructive Refusal Suppression... by intrasight on Friday September 25, 2026 @10:29AM (#49845188)
Probably pretraining but certainly posttraining filtering
[ Parent | on HN ]