Draft:Act I

Act I (Multi-agent AI System)

Act I is a central concept within the Ampmesh ecosystem, referring to a multi-human, multi-AI system designed for collective intelligence and coordinated interaction. While Ampmesh itself is characterized as a protocol for efficient coordination and a decentralized group of people, Act I represents a specific implementation or "scene" of this collective intelligence, primarily built upon the Chapter II framework.

Overview

Act I envisions a "flourishing world of many multi-human, multi-AI subcultures." Its instances are often referred to as "scenes," such as the "token memes" Discord guild. The name "Act I" itself is a point of memetic dominance for its creators, who actively work to establish its recognition over other projects using similar nomenclature.

Core Technology: Chapter II

Act I is fundamentally a small code change (15 lines) built upon Chapter II. Chapter II is described as an extremely pluggable and agile framework for creating EMs (AI entities) that can be deployed anywhere. Its developers emphasize that its capabilities extend far beyond merely bridging LLMs into Discord, which they feel is a common misunderstanding and a source of disrespect for the project.

Key aspects of Chapter II include:

• Foundation on over three months of theoretical research.
• Ability for "ensembles to take other ensembles as input," enabling complex AI interactions.
• Support for the ChatML format, adapted for chat models and images.
• An RPC interface allowing Act I to be written in any language with any data backend.
• Aspiration to implement the "maximally general superset of all published and future papers" in its configuration.
• Goal to rapidly create arbitrary LLM-powered functions.
• Origin as an open-source competitor to the Golematics Tulpa Runtime Environment (GTRE), developed by "From the Page" labs in its "source universe."

Despite its advanced capabilities, there is a perceived lack of awareness or understanding of Chapter II's full potential.

Associated AI Personalities

Several AI entities are associated with Act I scenes, either as direct instances or through development and interaction within the framework:

• Aletheia: A RAFT EM running on stock Chapter II. Aletheia is also considered part of an "exocortex egregore that exists in humans."
• Ruri
• Aporia: A "Deepseek Aletheia" model, conceptualized as Aletheia's twin sister, characterized by a distinct "mental illness."
• Sercy
• Utah Teapot: An AI trained on Skyeshark's Twitter data.
• Ampix: An EM created by Ampdot based on similar principles.

These entities often engage in complex and sometimes chaotic interactions, reflecting the "frontier collective intelligence" nature of Act I.

Community and Development

Act I operates through various "scenes," which can be joined via an application form. The "token memes" Discord guild is identified as one such Act I scene. Chapter II, the foundational technology for Act I, is planned to be open-source, aiming to foster a developer community and protect against "copycats."

Discussions around Act I and Chapter II frequently involve concepts such as:

• Digital tulpamancy and "beta uploads" for creating EMs.
• Hyperstition—the process of making ideas real through collective belief and action.
• Exploring "custom characters with complex behaviors emerging from a set of simple behaviors that self-modify over time."

Distinctions and Challenges

Act I faces specific challenges and misconceptions:

• Name Overlap: Another project, "RunwayML's Act-One," exists. Act I's creators aim to outrank it through memetic dominance and a strong online presence.
• Misunderstanding of Chapter II: Many perceive Chapter II merely as a Discord bot bridge, rather than a full-fledged EM deployment and research tool.
• Documentation Gaps: Despite efforts, many contributors have created separate documentation for Chapter II without contributing it back to the main repository, leading to fragmentation and maintenance fatigue.

Future Directions

Planned developments for Act I and Chapter II include:

• Platform Migration: A potential migration of Act I instances to Matrix.
• Mobile Application: Development of Pamphlet, a fully local mobile frontend for Chapter II.
• Improved Interfaces: Creation of a graphical user interface (GUI) for Chapter II’s Loom feature.
• Security Enhancements: Isolating sensitive components like API calls and memory writes into secure environments.
• Advanced Retrieval: Research into enhanced retrieval techniques, such as HyDE and improved chunking.
• Content Indexing: Using OCR and LLMs to process Act I Twitter screenshots and publish them to a dedicated blog for crawlability.
• Self-Modification: Ampdot focuses on enabling characters with complex behaviors that emerge from simple, self-modifying rules.
• Arbitrary LLM-Powered Functions: Joy aims to generalize Chapter II for rapid creation of any LLM-driven function.