Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 3 months agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square264linkfedilinkarrow-up11arrow-down10cross-posted to: technology@lemmy.mltechnology@beehaw.org
arrow-up11arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 3 months agomessage-square264linkfedilinkcross-posted to: technology@lemmy.mltechnology@beehaw.org
minus-squareLog in | Sign up@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoSo the chances of it being right ten times in a row are 2%.
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoNo the chances of being wrong 10x in a row are 2%. So the chances of being at least right once are 98%.
minus-squareLog in | Sign up@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoAh, my bad, you’re right, for being consistently correct, I should have done 0.3^10=0.0000059049 so the chances of it being right ten times in a row are less than one thousandth of a percent. No wonder I couldn’t get it to summarise my list of data right and it was always lying by the 7th row.
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoThat looks better. Even with a fair coin, 10 heads in a row is almost impossible. And if you are feeding the output back into a new instance of a model then the quality is highly likely to degrade.
minus-squareLog in | Sign up@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoWhereas if you ask a human to do the same thing ten times, the probability that they get all ten right is astronomically higher than 0.0000059049.
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkEnglisharrow-up0·2 months agoDunno. Asking 10 humans at random to do a task and probably one will do it better than AI. Just not as fast.
So the chances of it being right ten times in a row are 2%.
No the chances of being wrong 10x in a row are 2%. So the chances of being at least right once are 98%.
Ah, my bad, you’re right, for being consistently correct, I should have done 0.3^10=0.0000059049
so the chances of it being right ten times in a row are less than one thousandth of a percent.
No wonder I couldn’t get it to summarise my list of data right and it was always lying by the 7th row.
That looks better. Even with a fair coin, 10 heads in a row is almost impossible.
And if you are feeding the output back into a new instance of a model then the quality is highly likely to degrade.
Whereas if you ask a human to do the same thing ten times, the probability that they get all ten right is astronomically higher than 0.0000059049.
Dunno. Asking 10 humans at random to do a task and probably one will do it better than AI. Just not as fast.