OpenAI
filed
Disrupting a coordinated model-distillation campaign
read it at the source — OpenAI →
“Learn how OpenAI disrupted a campaign to extract protected model reasoning and is strengthening defenses against adversarial distillation.”
What was said about it
OpenAI says Moonshot attempted to manipulate their models to disclose reasoning chains as part of a distillation effort.
18 likes
Also on the board
-
3 outlets
-
3 outlets
-
3 outlets
-
2 outlets
-
The Verge