I can't actually find that statement in the video but if he said that, I'd say it's brilliant.
The thing about the "AI safety" nerds is ... if some vast corporate entity were to create a truly god-like computer program, whether the program escapes the control of its masters is a problem for the corporate entity but just fact of thing being created and being in the hands of this entity would be the problem everyone else would face.
And more broadly, if we haven't done much about the general sickness of society, what chance should we expect against a final problem of this beyond-human-control AI.
Bad "reductionism" points toward too simplistic solution. Good "reductionism" debunks bad but supposedly-sophisticated solutions. This is Good reductionism imo.
The thing about the "AI safety" nerds is ... if some vast corporate entity were to create a truly god-like computer program, whether the program escapes the control of its masters is a problem for the corporate entity but just fact of thing being created and being in the hands of this entity would be the problem everyone else would face.
And more broadly, if we haven't done much about the general sickness of society, what chance should we expect against a final problem of this beyond-human-control AI.
Bad "reductionism" points toward too simplistic solution. Good "reductionism" debunks bad but supposedly-sophisticated solutions. This is Good reductionism imo.