This is really quite enraging to read. Stop building bigger AIs! It’s that simple. The rest of the details regarding whether, when and how to restart can be worked out later.
AI labs saying they don’t know how to respond here is like fossil fuel companies saying they don’t know what they can do to mitigate climate change. It’s sounds as if actually stopping is so inconceivable that the response is to come up with complicated frameworks that sound like they might (eventually) lead to stopping, but in fact are doing everything they can to allow the companies to continue business as usual.
Yeah, Dario pretty explicitly describes liking RSPs in part because they minimally constrain continued scaling:
“I mean one way to think about it is like the responsible scaling plan doesn’t slow you down except where it’s absolutely necessary. It only slows you down where it’s like there’s a critical danger in this specific place, with this specific type of model, therefore you need to slow down.” (Logan Bartlett interview, h/t Joe_Collman).
This is really quite enraging to read. Stop building bigger AIs! It’s that simple. The rest of the details regarding whether, when and how to restart can be worked out later.
AI labs saying they don’t know how to respond here is like fossil fuel companies saying they don’t know what they can do to mitigate climate change. It’s sounds as if actually stopping is so inconceivable that the response is to come up with complicated frameworks that sound like they might (eventually) lead to stopping, but in fact are doing everything they can to allow the companies to continue business as usual.
Yeah, Dario pretty explicitly describes liking RSPs in part because they minimally constrain continued scaling: