Niko Grupen Notes Intuitive AI Reasoning Traces at Harvey
Compares reasoning traces from parametric memory plus study notes to coding agents' outputs.
TLDR
Niko Grupen, Head of Applied Research at Harvey, posted about an interpretability result from work with EngramLab on law firm knowledge. He stated that reasoning traces from parametric memory plus study notes are much more intuitive than the interleaved bash commands produced by coding agents. Grupen indicated this difference affects the UX of long-horizon agents. The post includes an attachment showing a clean UI with a user query.
Combined views
12.5K
1 Source, first seen ago