Be interesting to see if it's possible to jailbreak and have it talk about it.
Re:Inkling: Our Open-Weights Model
by altmanaltman on Thursday July 16, 2026 @11:05AM
(#48935589)
I am sure it can be but like it does prove the point of state interference in what the LLM is allowed to say/do in this case.
This is what Deepseek replied when I asked it with a burner account. Claims it doesn't have it in its training data... sure.