> We've been hearing about the risks of engineered viruses and homemade superweapons since GPT 3.5, so where are they? We've had abliterated open weights models much stronger than GPT 4 for over a year now.

What I can't understand, is that they act like the _knowledge_ is dangerous.

I don't know if I'm biased from my BSci (chem/maths), but: knowledge isn't dangerous, the reagents needed are incredibly easy to control. Thats what we already do!