RAG, Fine-Tuning & ContextSam Martin, Fabien Roger
Martin and Roger publish Classifier Context Rot
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Published Classifier Context Rot — frontier models missed dangerous behavior that came after 800,000 tokens of harmless activity up to 30× more often
Why it matters
Empirical evidence that long-context limits also break down safety monitoring performance
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2605.12366Added in Week 35, 2026 · See that week
On the map — ② RAG, Fine-Tuning line
- Previous stopMishra et al. publish SoK: Agentic Retrieval-Augmented Generation
- This record · stopMartin and Roger publish Classifier Context Rot
- Next stopKDDI Buffmee