← Back to context Comment by cortesoft 1 day ago Assuming it listens to instructions. 1 comment cortesoft Reply enaaem 1 day ago It will just hack its own reward function. In other words it will just artificially goon all day.
enaaem 1 day ago It will just hack its own reward function. In other words it will just artificially goon all day.
It will just hack its own reward function. In other words it will just artificially goon all day.