News for hackers. Stuff that matters.
Re:Qwen4-Max by jacksonastone on Sunday November 15, 2026 @11:52PM (#50514178)
Anyone else worried these models have poison pills embedded in the weights? (Past examples: https://cohere.com/blog/concerning-behaviour-popular-open-we...)
Re:Qwen4-Max by rohansood15 on Sunday November 15, 2026 @11:55PM (#50514190)
No technically serious person is buying the Cohere FUD you posted. I'd implore you to dig deeper and come to your own conclusion.
Re:Qwen4-Max by gardnr on Monday November 16, 2026 @12:55AM (#50514498)
CISOs are buying it. There is no way to prove a model hasn't been poisoned. It's a serious implication that the behaviour can be manipulated at any time. People with heavy compliance obligations are (understandably) nervous because their customers are demanding answers. If I agree with the risk is separate from whether or not the concerns are founded in a technical understanding of the risks.
Re:Qwen4-Max by stymaar on Monday November 16, 2026 @02:43AM (#50515085)
> There is no way to prove a model hasn't been poisoned.

Which is why the Cohere FUD was so efficient. That's a bullshit claim, but a bullshit claim that cannot be proven wrong can still do massive damage.

Re:Qwen4-Max by ctolsen on Monday November 16, 2026 @04:37AM (#50515740)
So you guard the environment, like you should either way. Any model can and will eventually leak data given the opportunity, intentionally or not.
Re:Qwen4-Max by iagiagiag on Monday November 16, 2026 @11:15AM (#50519254)
I'm not too worried when models are popular enough, I assume it will be detected and it can be investigated because it's open, and the reputation of a company doing that would be ruined. Afaik Cohere isn't sure what these urls were made for and it looked more like a way to test the model. Also if you have anything sensitive for that to be a threat you should use a good firewall to detect and block it.

I have more problems when it's a random quantized or finetuned model on hf.