Brian, how much input is required to arrive at such an assessment? And what are the error bars?
Also: Would love to see this reversed like with #DeepDream, to generate an utterance from someone with a specific profile!
-
-
-
Florian, thanks is for asking. The system is designed to extract indicators and adjust to present a compatible type for the user. It is thus bi-directional. The error rate is very much improved-96%.1/2
- 3 more replies
New conversation -
-
-
Wow! this looks super interesting! Are you able to share any more?
-
Michal, thank you! It is one of the protocols I use to ascertain the personality indicators and context of that person. Once we establish this, the system dynamically adjusts to the personality indicators of the user.
- 2 more replies
New conversation -
-
-
Good lord, Brian!
There is a lot to unpack here. Listen folks, don’t hurt yourself or your organization trying to do this without guidance. Just Ask Brian! #JAB

-
Robert, wow thank you! I really appreciate it.
End of conversation
New conversation -
-
-
Whoa , what magical powers is this?
-
Eric, wow thank you. Just some aspects I have been working on for a few years. I have been achieving very high accuracy on almost 500 points. I feel compelled to let folks know this can be done. It has awesome power for good and not so good.
End of conversation
New conversation -
-
-
Holy crap. That is awesome. If you ever release that into the wild if love to play around with it.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Now we're cooking!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.