Some good sources on belief research referenced in this article:
The Strength of Our Political Loyalties Changes Our Actual Beliefs
- Kristoffer Nimark, an economist at Cornell, and Savitar Sundaresan, of Imperial College London, describe belief polarization this way: “The beliefs of ex ante identical agents over time can cluster in two distinct groups at opposite ends of the belief space.” (Inattention and belief polarization)
SBIRs
- More writing
- Work on RCSNN – Made some good progress. The generated code is cleaner and easier to read. Need to start testing that it draws and runs correctly
GPT Agents
- Test and validate balanced pull
- Run balanced and proportional 10,000 tweet pulls for ivermectin and plaxovid
- Try running Top2Vec on tweets to see what the topic spaces look like
- Try to get some threads in those two spaces and use those to show trajectories through topics
- If there are enough intersecting trajectories, then create narrative embedding space