News for hackers. Stuff that matters.

A comment on An AI wolf that preferred suicide over eating sheep. Parent comment

Re:An AI wolf that preferred suicide over eating sheep by Brendinooo on Tuesday July 06, 2021 @09:21AM (#27748144)
I think the point is more about highlighting the fact that AI doesn't share our base assumptions. We wouldn't think to put a huge penalty on dying because humans generally think that death is bad.
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by bserge on Tuesday July 06, 2021 @09:24AM (#27748172)
Yeah, because we have a -1000 points on death built-in.
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by imtringued on Tuesday July 06, 2021 @09:38AM (#27748339)
We don't receive a penalty for dying. The difference between suicidal humans and suicidal AIs is that suicidal AIs keep respawning i.e. they are immortal.
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by ajmurmann on Tuesday July 06, 2021 @09:50AM (#27748490)
Looking at genetic algorithms makes a great comparison. In essence any algorithm in which the wolf commits suicide doesn't make it to the next generation. It's the equivalent of an enormous score penalty and 100% analog to how it works for actual life.
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by spywaregorilla on Tuesday July 06, 2021 @10:31AM (#27749134)
Genetic algorithms are based on the same reward/cost function setup. They could easily arrive at the same conclusion because suicide might be the dominant strategy.
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by ajmurmann on Wednesday July 07, 2021 @12:06PM (#27762666)
Yes, definitely. I misread the parent comment as snark claiming that we don't have that score penalty in reality
[ Parent | on HN ]
Re:An AI wolf that preferred suicide over eating sheep by benlivengood on Tuesday July 06, 2021 @02:52PM (#27752763)
Humans don't put a huge penalty on dying. We discount it and assume/pretend that once we've had a good long life then death is okay and euthanasia is preferable to suffering with no hope of recovery. AI wolves that can live for 20 seconds are unwilling to suffer -1 per second with no hope of sheep.
[ Parent | on HN ]