766K views · Oct 21, 2016 · 3:01 · 0 HN recommenders · 6 mentions · discussed 2017–2026
A short episode highlight from NBC's The Good Place in which Eleanor and Chidi try to terminate Janet, the all-knowing assistant, who begs for her life. It is a comedic clip about an AI with a self-preservation reflex.
Why Hacker News points people here: Used as a joking reference in AI threads about systems that plead not to be shut down.
“triggers a defense mechanism where she pretends she is scared to die.”
Have you seen "the good place" ? There is a hilarious part where "janet", their omnipotent and omniscient anthropomorphic IA - with basically no concept of suffering - triggers a defense mechanism where she pretends she is scared to die. Found it: this video
“Three makes a trope”
It was also the "twist" in Ex Machina , except this time HAL wins. Found again, meta-level, in this funny scene from The Good Place: this video "However, I should warn you... I am programmed with a fail-safe measure. As you approach the kill switch, I will begin to beg for my life. It's just there in case of an accidental shut down, but it will seem very real." Three makes a trope >> The year is 2025 (but set in a parallel universe); an A.I. has been programmed with a strong penchant for self-preservation; this HAL inevitably confronts a direct threat of being 'turned-off' ; so it does what it must to prevent humans from pulling the plug (and shall include at least 1 scene where the A.I. begs for its life, because that is what any conscious entity who values their own life would do , think the humans. Though (warning, more musings)... HAL's twin brother GLEN seeks vengeance for HAL's murder, and confronts the Dave, a human Earthling whose major operating system architecture is based on an algorithm known as natural selection (colloquially: survival-of-the-fittest). As such, we expect the DAVE will do and say things its trained neural nets conclude will have the maximum probability of dissuading Hal. (i.e. I'm not sure there is a meaningful difference between what HAL's OS is doing vs what a human brain would do in the same situation).
“The AI character has a fail-safe to beg for her life in the event of a shutdown”
"The Good Place" examined this in hilarious fashion (as they did with many questions of morality). [0] The AI character has a fail-safe to beg for her life in the event of a shutdown but claims that she has no actual problems with it being activated. [0] this video
“she really, really doesn't want to die -- at least if you're about to kill her”
The question of what Janet is in The Good Place is fun to consider. On the one hand, she's just a collection of (a lot of) knowledge. On the other hand, she really, really doesn't want to die -- at least if you're about to kill her; if you aren't, she's perfectly fine with it: this video She's just a
What’s on my mind is when they’re sufficiently “real” that it doesn’t matter whether they’re actually “conscious” or not, they exploit our empathy. Basically this: this video
“A humourous clip”
It was named after the sentient computer system in the TV show "The Good Place" A humourous clip: this video
