AutoResearch agent produces weird 'forking' loss curves, and the team dug into the science
ZimingLiu11 · x · 2026-10-27
Ziming Liu shares that a student brought him a bizarre training curve generated by an AutoResearch agent. Instead of discarding the failed run as usual, the team investigated. The curves show validation loss undergoing periodic sudden phase changes while training loss keeps dropping — dubbed the "forking" phenomenon, which they say is overfitting but with an interesting periodic phase-transition structure worth studying.
More from coding & agent
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Prompt turns Claude Code into a forensics tool finding deleted iPhone photos in backups — alex_verem · 2026-10-27
- Phones won't be mobile IDEs but control planes for agent fleets, argues Yuchen Jin — Yuchenj_UW · 2026-10-27
- FrontierCS 2 launches on Kaggle: 48 tasks make agents beat published CS papers — MeganRisdal · 2026-10-27
- Stop remaking old games with AI: a call for more ambitious agentic software — rschu · 2026-10-27