Anthropic researcher corrects circuit tracing paper: completeness score isn't faithfulness
JacobHHilton · x · 2026-10-20
Anthropic interpretability researcher Jacob Hilton issued a small correction to his circuit tracing work: the Figure 32 reference belongs to the companion paper 'Circuit Tracing: Revealing Computational Graphs in Language Models', and the 'graph completeness score' is more properly a measure of completeness, not faithfulness — a useful conceptual clarification for mechanistic interpretability readers.
More from Research
- Roboticist slams ICLR 'agentic robot planning' papers for ignoring classical planning and scaling lessons — KyleMorgenstein · 2026-10-20
- Berkeley Team Teaching AI Language Like a Baby Wins Schmidt Sciences Funding — begusgasper · 2026-10-20
- Brain-behavior AI framework finds 3 transdiagnostic biotypes in youth with ADHD and anxiety, in Nature Mental Health — bttyeo · 2026-10-20
- HoliWorld: scalable auto-labeling pipeline turns egocentric video into 3D/4D data — liuziwei7 · 2026-10-20
- mjfit peg benchmark under fire: cylinder-peg setup embeds a strong prior — YouJiacheng · 2026-10-20
- Industrial overcapacity enables scientific discovery: five cases from Michelson to Meta datacenters — charlesxjyang · 2026-10-20