Personal World Models
personalworldmodels.com · 5,048 words · saved by 1 readers
Memory is a compression problem. A life compressed the way a map compresses territory: built once, read by any model, owned by the person.
Memory is a compression problem. Current systems treat it as retrieval, which can say what happened but not what it means or what comes next. We introduce the Personal World Model (PWM): a life compressed the way a map compresses territory: what recurs becomes structure, and any model can read the structure and anticipate from it. GOLGI instantiates the framework: it ingests a real four-week photo archive, 720K tokens of raw life, into anchored entities, routines, and narratives an agent traverses in hundreds of tokens, on a pipeline that runs end-to-end on 4B on-device models. The agent…
saved by
related reading
- [2509.24527] Training Agents Inside of Scalable World Modelsarxiv.org
- How to train a frontier-level world modelnext-state.github.io
- pdfopenreview.net
- World Models: Computing the Uncomputablenotboring.co
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
- Agent memory as a file formatcalpaterson.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- Explore | alphaXivalphaxiv.org
- [2501.00663] Titans: Learning to Memorize at Test Timearxiv.org
- Engramme – Remember Everythingengramme.com
- NL.pdfabehrouz.github.io