AI Research Circle [members and +1s]
Monday · 2025-12-08 · 7:30 PM - 8:45 PM
We examined how linear directions in a model's activation space correspond to specific character traits like sycophancy, hallucination propensity, and moral reasoning. The group discussed what personality means for language models and the implications for alignment, safety, and developer tools. Paper: "Persona Vectors" (Chen et al., 2025).
More like this
Frontier Research Club brings robotics researchers, policy engineers, and hardware builders together for rigor-focused paper discussion with minimal slides and maximum critique. Expect depth-first conversation on embodied AI evaluation, failure modes, and what actually counts as evidence with capacity limited.
A focused reading group for researchers and builders working on world models and embodied AI, drawing people from Boston Dynamics, DeepMind, NVIDIA, Physical Intelligence, and Bay Area robotics startups. Expect keynotes, paper discussions, and technical roundtables on the frontier of robotic intelligence.
A curated reading group where robotics researchers and builders from DeepMind, Boston Dynamics, Tesla, and Bay Area startups dig into world models and embodied intelligence. Expect keynotes, open-floor discussions on papers that matter, and the scene's sharpest takes on what's actually moving the field forward.
Want more like this?
Get weekly picks matched to what you're into.