Road to Artificial General Intelligence

Re:Road to Artificial General Intelligence by dwohnitmok on Monday October 31, 2022 @10:23PM (#33416184)

I would be very interested in a set of benchmarks and intermediate goals for safe AGI (i.e. AGI that is aligned with human interests) rather than just AGI itself.

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by sdrg822 on Monday October 31, 2022 @10:38PM (#33416268)

Which humans?

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by mitthrowaway2 on Monday October 31, 2022 @10:52PM (#33416362)

That's an important question but I think even getting an AI to act in the interest of even one human would require solving 99.9% of the technical difficulty.

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by tough on Monday October 31, 2022 @11:26PM (#33416553)

There won't be any humans left once AGI is real

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by mitthrowaway2 on Monday October 31, 2022 @11:44PM (#33416647)

Yes, that's pretty much my point.

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by lgas on Tuesday November 01, 2022 @12:19AM (#33416856)

I volunteer.

[ Parent | on HN ]

Re:Road to Artificial General Intelligence by flandry93 on Monday October 31, 2022 @11:44PM (#33416642)

No such goals possible. See https://mflb.com/ai_alignment_1/index.html

[ Parent | on HN ]