> But the internal evidence is very convincing: try, for example, sticking yourself with a pin.
Systems don't need sentience to avoid self-harm: simply assign a large negative weight to self-harm. Now you need a big reward to offset it, making the system reluctant to perform such an action.
Systems don't need sentience to avoid self-harm: simply assign a large negative weight to self-harm. Now you need a big reward to offset it, making the system reluctant to perform such an action.