Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by camjohnson26 on Wednesday June 05, 2019 @05:51PM
(#20109536)
The existing implementations still have a long way to go. Here’s the chat I just had with cleverbot, the first thing it gave me after going to the site:
> Good afternoon. Do you know any good places to get dinner?
> Mot really.
> What about dessert?
> That's if you're a good bot.
> Not for you, for me.
> Okay..
Completely useless. I asked Alexa to find me the article on hacker news from today that talks about chat bots, she said “Sorry, I don’t know that one”
As a random, unscientific test it’s not very useful yet.
Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by mooman219 on Wednesday June 05, 2019 @07:00PM
(#20109976)
I remember reading that the user facing clever bot is really just for training. For competitions, a more robust dataset is used for the conversation and produces better results. [Citation needed]
Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by cududa on Wednesday June 05, 2019 @07:53PM
(#20110257)
...dude. The point never had anything to do with being the modern “PA” you’re imagining. It’s a chat bot designed 30+ years. It’s a neat (and at the time, breakthrough) for having conversations. It’s not intended to go find information for you..
Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by camjohnson26 on Thursday June 06, 2019 @10:13AM
(#20114738)
That’s the point. It might sound vaguely human but without the context to find and deliver information it’s completely useless
Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by icebraining on Thursday June 06, 2019 @01:55AM
(#20111961)
It's kinda amazing that SHRDLU still sounds advanced today, 50 years after it was created: https://en.wikipedia.org/wiki/SHRDLU
Re:Amazon Unveils New Alexa Dialog Modeling for Natural, Cro...
by taneq on Thursday June 06, 2019 @03:49AM
(#20112421)
It sounds advanced because it operated in an incredibility restricted context. It's impressive in the way that self-driving cars in the 80s were impressive because they worked at all.
Alexa has more complex requirements (it's funny when Cleverbot gives an occasional nonsensical response, but not so funny when Alexa unexpectedly orders you a $2,000 lawn gnome - okay, still kind of funny), but I definitely agree with you. I don't think this is a challenge that requires anything close to AGI, unless you want to start having truly insightful and philosophical conversations with a computer.