The discovery of some information theoretic limit to model learning (at least using current paradigms) can't come soon enough.

▲

thatsabadlook 2 hours ago | parent | next [-]

I am sure someone did it on the back of an envelope somewhere. It probably wouldn't translate well to the general public. Probably best to avoid such things

▲

optimalsolver 3 hours ago | parent | prev | next [-]

Only Claude (Shannon) can save us now.

▲

nutjob2 3 hours ago | parent [-]

He's spinning in his grave, but below the Nyquist limit

	▲	whacked_new 2 hours ago \| parent [-]
		Best comment in <duration>* * dependent on velocity

▲

AndrewKemendo an hour ago | parent | prev [-]

What problem would that solve?