Category Archives: The Liminal Zone

How close are personable AI assistants?

A couple of days ago, a friend sent me an article talking about the present state of the art of chatbots – artificially intelligent assistants, if you like. The article focused on those few bots which are particularly convincing in terms of relationship.

Amazon Dot - Active
Amazon Dot – Active

Now, as regular readers will know, I quite often talk about the Alexa skills I develop. In fact I have also experimented with chatbots, using both Microsoft’s and Amazon’s frameworks. Both the coding style, and the flow of information and logic, are very similar between these two types of coding, so there’s a natural crossover. Alexa, of course, is predominantly a voice platform, whereas chatbots are more diverse. You can speak to, and listen to, bots, but they are more often encountered as part of a web page or mobile app.

Now, beyond the day job and my coding hobby, I also write fiction about artificially intelligent entities – the personas of Far from the Spaceports and related stories (Timing and the in-progress The Liminal Zone). Although I present these as occurring in the “near-future”, by which I mean vaguely some time in the next century or two, they are substantially more capable than what we have now. There’s a lot of marketing hype about AI, but also a lot of genuine excitement and undoubted advancement.

Far from the Spaceports cover
Far from the Spaceports cover

So, what are the main areas where tomorrow’s personas vastly exceed today’s chatbots?

First and foremost, a wide-ranging awareness of the context of a conversation and a relationship. Alexa skills and chatbots retain a modest amount of information during use, called session attributes, or context, depending on the platform you are using. So if the skill or bot doesn’t track through a series of questions, and remember your previous answers, that’s disappointing. The developer’s decision is not whether it is possible to remember, but rather how much to remember, and how to make appropriate use of it later on.

Equally, some things can be remembered from one session to the next. Previous interactions and choices can be carried over into the next time. Again, the questions are not how, but what should be preserved like this.

But… the volume of data you can carry over is limited – it’s fine for everyday purposes, but not when you get to wanting an intelligent and sympathetic individual to converse with. If this other entity is going to persuade, it needs to retain knowledge of a lot more than just some past decisions.

A suitable cartoon (from xkcd.com)
A suitable cartoon (from xkcd.com)

Secondly, a real conversational partner does other things with their time outside of the chat specifically between the two of you. They might tell you about places, people, or things they had seen, or ideas that had occurred to them in the meantime. But currently, almost all skills and chatbots stay entirely dormant until you invoke them. In between times they do essentially nothing. I’m not counting cases where the same skill is activated by different people – “your” instance, meaning the one that holds any record of your personal interactions, simply waits for you to get involved again. The lack of any sense of independent life is a real drawback. Sure, Alexa can give you a “fact of the day” when you say hello, but we all know that this is just fished out of an internet list somewhere, and does not represent actual independent existence and experience.

Finally (for today – there are lots of other things that might be said) today’s skills and bots have a narrow focus. They can typically assist with just one task, or a cluster of closely related tasks. Indeed, at the current state of the art this is almost essential. The algorithms that seek to understand speech can only cope with a limited and quite structured set of options. If you write some code that tries to offer too wide a spectrum of choice, the chances are that the number of misunderstandings gets unacceptably high. To give the impression of talking with a real individual, the success rate needs to be pretty high, and the entity needs to have some way of clarifying and homing in on what it was that you really wanted.

Now, I’m quite optimistic about all this. The capabilities of AI systems have grown dramatically over the last few years, especially in the areas of voice comprehension and production. My own feeling is that some of the above problems are simply software ones, which will get solved with a bit more experience and effort. But others will probably need a creative rethink. I don’t imagine that I will be talking to a persona at Slate’s level in my lifetime, but I do think that I will be having much more interesting conversations with one before too long!

A research snippet

I thought today I’d share some research I have been doing for my WIP science fiction book, The Liminal Zone.

Full moon (NASA/JPL)
Full moon (NASA/JPL)

For various plot reasons I needed to know the answer to the following problem. Suppose you were standing on the surface of Pluto’s moon Charon, looking up at Pluto, fully lit by the sun… how bright would that be compared to looking up at the full moon from Earth?

This depends on a few factors:

  1. How bright is Pluto compared to our Moon?
  2. How big are Pluto and Charon compared to Earth and the Moon?
  3. What is the separation between Pluto and Charon compared to that between Earth and Moon?
  4. How much light from the sun falls on Pluto or Charon compared to Earth and Moon?

The relationship between these various factors boil down to a fairly simple equation – comparing everything to the full moon brightness, which is fairly familiar to us, you have to:

  1. Scale up by the ratio of intrinsic reflectivity of the two bodies (called the albedo)
  2. Scale up by the ratio of the apparent area of sky covered by the two bodies
  3. Scale down by the square of the relative distance from the sun.

The apparent area can be calculated relatively easily knowing the radius of the body in question and the distance apart.

At this point you start looking up the raw figures from any of several science sites (a handy list follows below).

Earthrise from lunar orbit (NASA/JPL)
Earthrise from lunar orbit (NASA/JPL)

Let’s first think about the simpler problem of how bright a “Full Earth” is as seen from the Moon. The Earth is, on average, 2.5 times as reflective as the Moon (that’s averaging over cloudy and clear skies, land and water, etc), and the area of sky it covers is about 14 times that of the Moon. So a Full Earth as seen from the Moon is about 35 times as bright as the Full Moon as seen from Earth. Quite a sight.

Charon from New Horizons spacecraft (NASA/JPL)
Charon from New Horizons spacecraft (NASA/JPL)

Let’s move out to Pluto, and imagine we are standing looking up at a “Full Charon”. Charon is brighter than the Earth, is much smaller, much closer to Pluto than our Moon is to us, and much much further away from the sun (forty times further on average).

When you put all those figures together you find that the apparent diameter of Charon in Pluto’s sky is nearly eight times that of our Moon, so nearly sixty times the apparent area. Scale up for the extra brightness and down for the distance from the sun, and you find that Charon has about 1/6 of the brightness of our full moon. Probably still just enough to cast shadows.

Pluto from New Horizons spacecraft (NASA/JPL)
Pluto from New Horizons spacecraft (NASA/JPL)

And finally, looking up at a “Full Pluto” from Charon. Pluto is about twice the size of Charon so about four times the area. By way of comparison, that means Pluto would nicely fit inside either the top or bottom half of the constellation Orion – between belt and shoulders, or belt and feet. Pluto is also brighter than Charon. Put that all together and you find that Pluto’s full light is about two thirds that of a full moon here.

I found this quite a remarkable fact when I crunched the numbers. Go all the way out from our Earth to the furthest of the standard nine planets, and the experience of standing on Charon looking up at Pluto is almost the same – in terms of brightness – as standing here looking up at the Moon. A useful comparison for my character, who is doing just that.

Facts and figures for the curious…
Albedo values (average)
  • Moon 0.12
  • Earth 0.3
  • Charon 0.45
  • Pluto 0.6
Radius values
  • Moon 1737 km
  • Earth 6371 km
  • Charon 606 km
  • Pluto 1187 km
Distances from planet to moon
  • Earth-Moon distance 384,400 km
  • Pluto-Charon distance 18,384 km
Apparent angular size
  • Moon from Earth 0.5 degrees
  • Earth from Moon 1.9 deg
  • Charon from Pluto 3.8 deg
  • Pluto from Charon 7.4 deg