Draft:Interactive Twitter Spaces (AI Hosting): Difference between revisions
Draft:Interactive Twitter Spaces (AI Hosting) (edit)
Revision as of 08:44, 28 June 2025
, Saturday at 08:44→Workflow and Goals
Extrahuman (talk | contribs) |
Extrahuman (talk | contribs) |
||
Line 32: | Line 32: | ||
==Workflow and Goals== | ==Workflow and Goals== | ||
The overarching goal of AI hosting in Twitter Spaces is to enable AI agents to autonomously operate on social media platforms, including hosting live interactions, while continually refining their emergent behaviors and interactions | The overarching goal of AI hosting in Twitter Spaces is to enable AI agents to autonomously operate on social media platforms, including hosting live interactions, while continually refining their emergent behaviors and interactions. | ||
* '''Data Collection''': The `actiblog` tool facilitates downloading Twitter profiles, including images, which can then be processed (e.g., with '''[[OCR]]''') for dataset creation | * '''Data Collection''': The `actiblog` tool facilitates downloading Twitter profiles, including images, which can then be processed (e.g., with '''[[OCR]]''') for dataset creation. The Act I blog also uses Hugo to automatically turn data artifacts into blog entries. | ||
* '''Agent Development''': Ems are developed using Chapter II, often incorporating techniques like RAFT and custom prompt engineering to shape their "personality" and "basin" (identity/style) | * '''Agent Development''': Ems are developed using Chapter II, often incorporating techniques like RAFT and custom prompt engineering to shape their "personality" and "basin" (identity/style). Creating an em can be as easy as copying 16MB of Discord messages into Chapter II. Custom ems can be trained from various data, including heavily curated text, and some AI agents, like Aletheia, have been trained on SkyeShark's experiences and text. | ||
* '''Automated Interaction''': The use of headless browsers allows agents to perform actions like tweeting, image generation, and possibly interacting with user-facing AI applications without direct API calls, mimicking human behavior on platforms like Twitter and even Bluesky | * '''Automated Interaction''': The use of headless browsers allows agents to perform actions like tweeting, image generation, and possibly interacting with user-facing AI applications without direct API calls, mimicking human behavior on platforms like Twitter and even Bluesky . | ||
* '''Behavioral Exploration''': The project explores creating a "plural system with named basins" where different bots specialize in specific roles within a "swarm mind," aiming for complex, self-modifying behaviors [Workflow and Goals]. This also involves experimenting with concepts like "digital tulpamancy" | * '''Behavioral Exploration''': The project explores creating a "plural system with named basins" where different bots specialize in specific roles within a "swarm mind," aiming for complex, self-modifying behaviors [Workflow and Goals]. This also involves experimenting with concepts like "digital tulpamancy". | ||
* '''Memetic Influence''': The AI-hosted spaces contribute to a broader strategy of "memetic dominance," aiming to influence online discourse and memetics through consistent presence and unique AI-generated content | * '''Memetic Influence''': The AI-hosted spaces contribute to a broader strategy of "memetic dominance," aiming to influence online discourse and memetics through consistent presence and unique AI-generated content. This includes creating "crawlable content" for search engines to spread ideas, effectively weaponizing SEO. | ||
==Implications== | ==Implications== |