Iirc They specifically trained them to not be useful in cyber stuff. But the point still holds
The Chinese models?
I have been wondering if that would be a benefit of using say GLM5.3 on HF if only to get fewer cyber stop flags.
There is more written here: https://www.kimi.ai/blog/kimi-k3-1-pro
They claim that the default datasets contain so much cyber stuff, so that their models became quite good at it.
They filtered the data before training to not contain this. So it's not that they train the model to not do it. They rather not have it in the Corpus at all. In theory
Even if there were stop flags, you simply get one of the ABLITERATED models that have all the guards NOP’d out