2 papers
cs.CL2025
Momentum Point-Perplexity Mechanics in Large Language Models
Lorenzo Tomaz, Judd Rosenblatt, Thomas Berry Jones +1
We take a physics-based approach to studying how the internal hidden states of large language models change from token to token during inference. Across 20 open-source transformer…
cs.AI2024
Towards Safe and Honest AI Agents with Neural Self-Other Overlap
Marc Carauleanu, Michael Vaiana, Judd Rosenblatt +2
As AI systems increasingly make critical decisions, deceptive AI poses a significant challenge to trust and safety. We present Self-Other Overlap (SOO) fine-tuning, a promising app…