Memory and coherence in narrative agents
How does an AI game master remember a whole campaign without lossy summaries, and keep track of what each character knows?
Independent applied AI research
FlowFab is where I study the questions that come up while building my own systems: a game master with long memory, agent architectures, and video made by language models. Each note says how it was tested and where it stops being true.
How does an AI game master remember a whole campaign without lossy summaries, and keep track of what each character knows?
How do you design agents with continuity and autonomy, and compare design proposals from several models fairly?
How far can an AI pipeline go in producing good explainer animation with little human intervention?
Personal projects. They are not research, but most of the research questions start here.
An AI game master for long solo campaigns. I wanted a GM who never cancels the session.
Animated explainer videos on YouTube, made with an LLM pipeline. Because I have a day job.
@anygiventhing ->A manager for small 3D printing farms, starting with mine. In development.
One printer, a lot of PLA, and the occasional first layer that refuses to stick.
Every note follows the same seven steps.