**Links to**: [[Coming abstractions]], [[Invention]], [[Science]], [[Semantic attractor]], [[Politics]], [[Narrative]], [[Theory-fiction]], [[Hyperstition]], etc. %% Cecile mention children stories: they are about mistakes you can make, you need to pass on these stories. Now that we don't have stories but tv, games, etc. In none of them you die, but in tv there is a distance (it's not the elders telling you) and in games you are reborn. Bedtime stories need to come back. %% ### [[Postulate]]: Fiction provides all of the learning, with (almost) none of the partaking risk. **Abstract**: This paper examines how, through the lens of active inference, fictions can be understood as semantic attractors enabling—relatively—risk-free learning. Fiction allows agents to creatively explore counterfactual scenarios and minimize uncertainty without exposure to “real-world” consequences. This mechanism frames both the evolutionary advantage and persistent appeal of narrative engagement. We treat aspects of punctuation and breath, following the work of Margaret Masterman. We also touch upon aspects of more “atomic” semantic attractors in the structures of language, such as rhyme and alliteration, as patterns which aid memory, communication and information retrieval policies. <small>Keywords: Fiction, Active inference, Fictional inference, Semantic attractor, Risk, Learning.</small> ### Introduction Fictional constructs can be understood as enabling explorative cognitive situations where communicating groups (or individual agents holding an internal, although always dialogical, thought process) can learn by simulating responses to high-stakes scenarios while maintaining corporeal integrity/safety, all the while plastically exploring their epistemic condition. Unlike “direct” experience, where prediction errors carry immediate consequences that need to be dealt with there and then, **fiction**—imagine: monsters, sci-fi, and plenty of other speculations—provides a neither-real-nor-impossible speculative space for testing predictive models against hypothetical outcomes. This speculative environment enables learning, in a way that often expresses itself as shared through narratives. The linguistic, transferrable nature of narrative structure therefore also allows for internal “parsing” and “epistemic foraging” at the level of the single agent. Moreover, the “grand narrative” that all fictions come to an end, that they can be understood as _chunks_, provides an additional factor which minimizes uncertainty about an agent’s engagement with a particular cultural product. On the contrary, in the context of experimental artistic practices such as performances where spectators are not informed of an event’s structure (such as when its ending is supposed to take place), we observe situations which lead to higher discomfort and even intolerance (see, e.g., the famous “Riot at the Rite”, people leaving the theater during the premiere of the Rite of Spring by Stravinsky, 1913). Additionally, as traditional kinds of fictions (movies, novels, jokes, etc.) and structures (exposition, climax, resolution) become more commonplace and well-known, these evolve to incorporate more uncertainty: leading to more cultural learning possibilities (respectively, with regard to the previous examples: expanded cinema and VR, experimental novels and publishing practices, ever-novel joke structures, etc.). By drawing on these kinds of examples, we will analyze how narrative structures act as “semantic attractors” by organizing *possible* world-states into explorable patterns. These patterns can be understood to function as probability-possibility landscapes for cultural belief-updating, allowing collectives to refine their predictive models through (repeated, rehearsed, newly imagined, etc.) engagement with fictional scenarios. Considering homo sapiens’ universal tendency towards narrative-sharing, this process of “fictional inference” may be fundamental to human learning capabilities, particularly in domains where direct experience would be prohibitively risky or impossible. After all, the only place where plans can begin, is in speculation about their effects. This analysis extends to all manner of media environments (such as VR), where possible worlds and (sometimes) interactive narratives provide increasingly sophisticated platforms for this type of risk-free learning. The proliferation of fictional modes across human cultures can be understood as the *ever more diverse* exploration of the learning-risk trade-off inherent in active inference. The productive capacity to engage with fictional scenarios represents one of the most interesting evolutionary solutions to the exploration-exploitation dilemma faced by all complex learning systems. The conclusion reached is that fictional inference’s capacity to facilitate learning in relative “safety” may represent one of the most interesting functions or adaptations in human cognitive evolution: from imagining-projecting gods and spirits, to the idea of a “Zeitgeist”, or even collectivity under a nation state (a rigid fiction), to our current understandings of whatever it is we call “AI”. The mechanisms of fictional inference therefore demand particular attention in the context of our futurological prospects. Please get in touch for a copy: [[ｃｏｎｔａｃｔ]]. %% [[Fiction notes]]