News for hackers. Stuff that matters.
Re:AI software clears high hurdles on IQ tests but still mak... by visarga on Saturday May 07, 2022 @01:51PM (#31296842)
> The problem is that "Link is reduced to a pile of ashes" should put Link into a "dead" state, and when in the "dead" state Link can't stand and be dazed.

Yes, this kind of problem is real. But recent papers show you can ask the model to do reasoning / chain of thought / rationales before coming up to the answer. They can do complex tasks in a series of small steps instead of trying to do it in one step and failing. I believe it's not a fundamental limitation, just a matter of "blurting out something stupid" vs "taking your time to think before you speak".

Re:AI software clears high hurdles on IQ tests but still mak... by mdp2021 on Sunday May 08, 2022 @05:17AM (#31302464)
> "taking your time to think before you speak"

One of the foremost core requirements for actual general intelligence.

Do you have any specific papers in mind?

Re:AI software clears high hurdles on IQ tests but still mak... by lostmsu on Sunday May 08, 2022 @12:10PM (#31305338)
I saw that mentioned in OPT175 release. How is the model forced to give reasoning?
Re:AI software clears high hurdles on IQ tests but still mak... by ChadNauseam on Monday May 09, 2022 @07:20AM (#31312804)
It’s not forced to, they just give a couple examples with reasoning and then the model figures out that that’s what it’s supposed to do