Modern LLMs are incredibly good compression algorithms, which can shed light on why autonomous data science agents don't overfit as much as you might think. arxiv.org/abs/2606.11045
Who's Who of AI
Aaron Roth
Professor at Penn, Amazon Scholar at AWS. Interested in machine learning, uncertainty quantification, game theory, privacy, fairness, and most of the intersections therein
What they're sharing
What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents arxiv.org
Articles & links
Their network
In Aaron Roth's orbit
Center = Aaron Roth. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.