Parallax

AI & ML interests

Building the science of belief elicitation for white-box auditing of frontier AI agents.

Recent Activity

gsarti  authored a paper about 2 months ago

Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

gsarti  authored a paper about 2 months ago

Distilling Formal Logic into Neural Spaces: A Kernel Alignment Approach for Signal Temporal Logic

gsarti  authored a paper about 2 months ago

Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers

View all activity

Team members 2