icymi, this is the core problem with current ML approaches to natural language understanding, in a single tweet with two images:https://twitter.com/GaryMarcus/status/1194081788307496960 …
-
This is also from GPT-2. But I'm not sure either of us have demonstrated anything important about machine cognition.pic.twitter.com/yDK081Hg5a
do me favor, try ten more times, and please tell me the % correct. (if you want, do the same with @Wolfram_Alpha)
-
-
Let's try a different game. Is this really worthwhile though? I don't think it is.pic.twitter.com/WUH6mb5zMz
-
i agree there are lots of challenges with WA, and outline some in http://rebooting.ai . But GPT-2 can't with any reliabilty answer questions like this, whereas WA can get a certain class of them with perfect reliability. That's a hint; not a complete solution.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.