Researchers are in fact exploring ways to customize the personalities of virtual assistants at scale; i.e., not simply by handcrafting. Microsoft: https://is.gd/qKxm34 Facebook: https://is.gd/BatzO0 @BrianRoemmele https://www.ft.com/content/f9a13062-5fd7-11e9-b285-3acd5d43599e … via @financialtimes
-
-
Replying to @jamesvlahos @FinancialTimes
James, indeed. You know the only true way to do this at scale is to use the protocols I have been so fortunate to discover in the 1980s one way is real-time Myers-Briggs Indictors. I use this in so many ways. A set personality is also a dead end, it’s about fluidity.
2 replies 0 retweets 4 likes -
To make it more human-like it has to be a bit unpredictable and moody, right? Having an actual argument with your virtual assistant would be super awesome
1 reply 0 retweets 2 likes -
Michal, indeed! You know I would frame this more as a sprited debate. It is quite invigorating actually to have your full context being presented back at you. It is a zen moment created by technology.
1 reply 0 retweets 1 like -
Absolutely! That is why I am so excited about the intelligence amplifier you are tweeting about. My only fear (probably because I don't understand it enough) is that it may possibly create my own contextual echo chamber.
1 reply 0 retweets 2 likes
Michal, this is a very good fear to have and one of the reasons I decloaked in 2019. There are a few astute and human aligned ways to build this stuff and regrettably far to many ways to build it the wrong way. The fundamental issue is who is building this stuff and why.
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.