recursivelabsai/Self-Tracing

Building on Anthropic's Circuit Tracer, Neuronpedia, Ameisen et al. (2025) and Lindsey et al. (2025), we attempt to extend the paradigm with adaptive context engineering to enable recursive self-interpretation, where models continuously monitor, trace, and explain their own decision processes

2 best points · 0 comments · 1 Hacker News post · 74 GitHub stars · View on GitHub

Hacker News discussions

• Self-tracing large language models (2 points, 0 comments, by davidkimai, 2025-06-02)