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.

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.

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.