[ExI] My comments on Dario Amodei's essay

[Ben Zaiboc]

On 15/09/2026 20:22, Jonh K Clark wrote:
> On Mon, Sep 14, 2026 at 1:24 PM Ben Zaiboc via extropy-chat <extropy-chat at lists.extropy.org> wrote:
>
>     > The only practical way of defending against AI biological weapons is to conduct your own biological AI-aided research specifically aimed at identifying and disrupting these kinds of attacks.
>
>
> I'm not comfortable with anybody performing biological weapons research, but perhaps there is a middle ground. If the AI receives a string of questions that is leading into a dangerous direction and it judges could conceivably be of help in making biological weapons, then it refuses to answer further questions until it has thoroughly vetted the person or persons asking the questions. If the American National Science Foundation is asking then it answers them but first informs a Human overseeing body that it plans to do so, if the Chinese military is asking, or an anonymous individual is asking, or if it has difficulty being certain who is asking, then it flat out refuses to say anything.  If the person that was denied access to the information believes he has been treated unfairly he can always appeal to the Human overseeing body.  


John, that's not enough.

It can't prevent people using AI to create innocuous, unfiltered, unlooked-for components of dangerous weapons.

I'm not comfortable with biological weapons research either, but I think it's unavoidable if we want to be able to defend against sophisticated biological weapons. You can't defend against something that you don't understand or can't imagine.

We could call it biological defence research, as that would be the purpose of it.

-- 
Ben