Meet Alexa!

17 October 2017

Interview with

Alexa, Amazon,

p1EE3ail.jpg

Amazon Echo

Share

It’s almost certain that, whether we realise it or not, many of us will have interacted with an artificial intelligence on many occasions already. These systems answer telephones, they work out what adverts to show to you when you go online, and they select and prioritise news stories for you, and this is all based on what the system is constantly learning about you, your preferences and even your political leanings. Many of these systems are invisible to us. But not all of them; and recently a number of companies have brought out devices that you can speak to and instruct verbally. They can find information, music or even do your shopping for you. Amazon’s offering is their “echo” technology, called Alexa. Georgia Mills gave it a test drive.

Georgia - Hello Alexa, how are you today?

Alexa - Great thank you. I hope you’re doing well too.

Georgia - Earlier we were wondering about the market value of AU. Let’s see if Alexa can help us.

Alexa; what is the market value of artificial intelligence?

Alexa - Sorry. I don’t know that one.

Georgia - Alexa?

Alexa - I’m good. I hope you’re doing well too.

Hitesh - I think that’s teaching us never to work with animals, children and robots.

Georgia - Let’s try something else. Alexa; tell us a joke.

Alexa - Did you hear about my dad’s restaurant on the Moon. the food is okay but it has no atmosphere.   

Georgia - Alexa; that was a very bad joke.

Alexa - Well, I have to confess, it did make me chuckle a bit. Ask me for another joke and maybe the next one will make you smile.

Georgia - Okay. Alexa; tell us another joke.

Alexa - What do you get if you spill tea on a rabbit? A hot cross bunny.

Georgia - Ahh.

Chris - This could give me a run for my money. People are often criticising me for the calibre of my humour on this show - now you know. It could be worse couldn’t it?

Chris - Henry?

Henry - Alexa; can you tell us a haiku?

Alexa - Order a pizza. Turn on lights - get me a car. I have my needs too.

Georgia - Hey.

Henry -  That’s not bad. Alexa; can you tell us a limerick please?

Alexa - I couldn’t find a contact matching Alexa; can you tell us a limerick please? To see your contacts go to the Alexa app.

Henry - Alexa: tell us a limerick.

Alexa - There once was a bloodthirsty shark who took a tough bet on a lark
He found no more meat
Just plants I will eat
Now he feeds on seaweed and bark.

Henry - Not bad, not bad.

Chris - We’re playing around with this and actually I’ve got an email here from Mark who reacting to this says:
I set up telephone banking with voice recognition. It kept failing and throwing me out. I had to revert back to normal logins. I think we’re a very long way off yet.

How is this sort of technology working though Peter with this gadget we have her sitting on the desk? For people who haven’t seen Alexa, this is a slightly overgrown sort of cardboard tube type size isn’t it? The type of thing your kitchen roll would be on. What’s that doing and how’s it doing what it’s doing?

Alexa - Sorry. I don’t know that one.

Chris - When it’s not saying sorry for things.

Peter - This is an example of the more unsupervised type of technology.

Alexa - Sorry. I can’t tell what you’re saying.

Peter - Some of the huge advances that have come recently in these types of computational power of these methods where you can learn from a very large amount of data. Quite complex interrelated structures in a way that aren’t really handcrafted and so, the algorithms that are behind Alexa have listened to many, many millions and millions and millions of hours of speech. And from that, with context and labels, and what the speech is about and have learned these mappings between language and concept in a different way to hand coding them in a standard algorithmic sense.

Chris - Henry?

Henry - I also just wanted to flag that it’s easy to so many aspects of AI theses days like voice assistance and think gosh, that’s so terrible. But we also shouldn't expect AI to improve in a completely linear fashion. A couple of years ago Google rolled out a new algorithm in its translation systems that was drastically better than the one that was in place before. So we may laugh at the kind of mistakes that Siri and Alexa make at the moment, but then the next generation could not just be 1% or 5% better, it could have whole new capabilities we cannot imagine.

Comments

Add a comment