July 16, 2003

AI and authorship

by Michael Mateas · , 12:14 pm

The post Responsive Narratives (and its comments) raises the question of whether there lies anything in between brute force authoring approaches and building a human-level AI. This question is important not just for interactive drama, but for Expressive AI (AI-based art and entertainment) in general. In a brute force authoring approach, the artist lovingly hand-crafts material (e.g. animation, text, images, etc.) for every possible context, for all possible interactions. In the AI-complete approach, the artist somehow describes their intention at a very high level (e.g. the high-level motivations of characters), and the system auto-magically grounds this high-level description with concrete representations for different contexts (e.g. generated animation, generated text, generated images) and for all possible interactions. There are good reasons to seek a middle ground besides the current technical impossibility of AI-complete approaches.

Hand-crafted material tends to be high quality because the artist can directly employ her skills in shaping the material. In AI-based art what you want is to somehow have the AI architecture help you generate material (manage combinatorics) while supporting fine-grained authorial control. This seeming contradiction can be resolved by approaches that provide multiple levels of abstraction, and allow the author to move up and down these levels of abstraction while creating material. In Façade, this plays out by having several different custom languages for authoring different parts of the experience, as well as different subsystems that are built using these languages. For example, each dramatic beat has a collection of character goals and behaviors that are active during the beat. Some of these goals are special “beat goals”, dramatically significant moments necessary to carry out the beat. During the beat, these beat goals are sequenced in such a way as to carry out the beat while responding to player interaction. Goals and behaviors are written in ABL, a custom behavior language for believable agents. The “specialness” of beat goals, their ability to dynamically resequence as player interaction occurs, is handled by additional code written in the ABL language. Even just within the ABL code in Façade, as authors we moved between several hierarchical levels, writing the code that gives beat goals their special properties (this code is infrequently changed), for each beat sometimes writing code that provides custom sequencing logic for beat goals within that beat, and for each beat writing the beat goals and behaviors themselves that carry out dramatically significant behaviors.

If one views AI-complete approaches as the holy grail, rather than seeking a middle ground, this leads to a different technical and artistic agenda, one focused on automating the author rather than providing a rich combinatoric authoring framework. For example, when building an architecture for dramatic beats, such an approach might try to capture some general logic of dramatic beats, seal this general logic into a black box that automatically manages activity within a beat, and force authors to use this black box. Of course authors would immediately want to do things that the “general logic” doesn’t handle. Viewing the problem as “automation” tends to lead to rigid black boxes. An author-centric approach leads to soft, permeable hierarchies and custom languages.

I agree with Andrew that high-agency interactive drama will inevitably be technology-heavy. There is no magic design bullet that, if you just conceive of interactive story the right way, allows you to build rich interactive dramas by writing a bunch of C code using standard techniques. When we started this project, I think Andrew thought that we could get maybe 50% of the way there through good interaction design and story design. He now feels that good design, on its own, won’t get you even that far. It’s interesting that for me, I never thought that good design, on its own, would get us anywhere. That’s partly because, in my approach to AI-based art and entertainment, the design thinking is actually done through an architecture – that is, the AI architecture and the design co-evolve. Without the architecture, the only design work you can do is some kind of wish list. But the detailed design requires this architectural co-evolution. Even the wish-list isn’t really understood until the architectural work begins. The tradeoffs between items on the wish-list aren’t apparent without an architecture. And the architecture suggests new design directions, new conceptual opportunities, that the artist doesn’t even conceive of except when thinking through code.

In this post, Andrew describes his design approach for writing beats in Façade, emphasizing that he starts with a piece of paper, far from the details of architecture and code. I similarly start with a description of what I want a beat to accomplish. But I claim that we wouldn’t be able to do this except that we’ve already reached a stable state in the co-evolution of design and architecture. When we write these high-level descriptions, we’re doing it with a deep understanding of beats, beat goals, natural language contexts, and other abstractions defined by our architecture. We wouldn’t know how to write these high-level descriptions without this architectural understanding.

3 Responses to “AI and authorship”

  1. Nicolas Szilas Says:

    Seeing the AI-complete approaches as focusing « on automating the author rather than providing a rich combinatoric authoring framework » gives a bad and wrong image of AI-based art and entertainment. It makes believe that, as it was often said 30 years ago, AI aims at replacing man, in every domain. I don’t think anyone believes this in this group!!

    As we have discussed earlier, AI-complete Interactive Drama means that the author is writing at a higher level, that’s all. We do not automate the author, we automate the production of the sequence of content provided to the audience, but, fundamentally (and ideally), the quality of the work does not lies in this content : it lies in the rules that produce this content, which should remain the responsibility of the author. A future audience would not say : « what an nice animation ! » but « what a nice way to react to what I have juste done before ! ».

    Having said that, I even wonder if it is not dangerous to focus on well hand-crafted content, since anyway, it would never be as well designed as non interactive content. Thus, in a brute force authoring approach, the fact that « the artist lovingly hand-crafts material » might be detrimental to the work, because it would distract from what really matters : what happens in reaction to each action (the rule or procedure).

    This position is voluntary extreme: any real interactive drama will combine “pure” interactive design (designing rules) and content/material design. But I think (I hope) it helps thinking about Interactive Drama and Art.

  2. Michael Says:


    The two positions, total automation and total hand-crafting of material, are purposefully extreme positions that I use to try to understand the middle ground better. I’m not saying that I or anyone else should hold these extreme positions.

    Regarding the AI-complete approach being automation of the author, I have seen this position brought up in the literature. For example, ludologists have used this position to argue that story and interactivity and fundamentally at odds because interactive story would require such an AI-complete author, and that this is impossible (or at least, too far off to matter).

    I think looking at the AI-complete position is useful because it foregrounds that not only do we not need to achieve this in order to make forward progress in AI-based art, but that in fact it is the wrong vision because it misses authorship. I brought up the other end of the spectrum precisely to foreground the importance of authorship.

    The term “AI-complete” usually refers to hypothetical AI systems that have human-level intelligence. The term is often used in describing that solving supposed subproblems of AI in fact require solving the whole thing, e.g.: “Scene understanding is AI-complete.”, We’d need an AI-complete system to solve natural language understanding.” (AI people borrow this way of talking from computational complexity theorists who talk about such things as “NP-complete”.)

    So when you say

    As we have discussed earlier, AI-complete Interactive Drama means that the author is writing at a higher level, that’s all.

    I’m not sure if you really mean AI-complete, because then what you’re saying is that we do need human level intelligence before we can do interactive drama, or more generally, AI-based art. The point of my post was to say that we don’t, and that in fact thinking this way is not a fruitful way to proceed in doing Expressive AI.

    I think we agree, and may have just been led astray by terminology.

  3. Nicolas Szilas Says:

    Yes, I understood the term “AI-complete” differently.

    I am interested in the case where AI calculates all the “low” level: animations, speech and dialogs, actions/behavior choice, music, cameras, etc. In that case, the author specifies the thematic, the actions happening in the story, various features describing the story (depending on the story model chosen), parameters of a user model, etc. The AI generates all the rest. It is a full automation not of author but of narration (the act of telling on thing after another).

    Well, we are very far from such a level of automation. I am not sure this is a middle ground at all! But I feel that in the long term, the field of Interactive Drama should evolve towards such a situation.

Powered by WordPress