BPPV is not fun. Still have some inner-ear hangover

Inside the Scam – Frontline

• When Chris Colocousis first met a woman named Eliza on Facebook, he wasn’t sure she was real. What started as an online romance turned out to be an investment scam.

Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

• AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.

Tasks

• Take the Bruni out for a spin. Done. Shifting is a bit ragged, so it’s going back in
• Started looking at the process of getting an A-file.
  • Got a USCIS account, and found out how to get these things certified

SBIRs

• Start thinking about the RAG vectorstore. I think at this point it could simply be a pickled dataframe that’s loaded locally.
• Tweaked the ChatUnit to handle images. NOT TESTED
• Added an include_list to the model explorer which makes everything much more usable. I should add a way to sort the list of dicts by name, type, or cost