Frontier LLMs miss dangerous actions in long coding agent transcripts 2-30 times more often after hundreds of thousands of benign tokens.
Constitutional Black-Box Monitoring for Scheming in
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Classifier Context Rot: Monitor Performance Degrades with Context Length
Frontier LLMs miss dangerous actions in long coding agent transcripts 2-30 times more often after hundreds of thousands of benign tokens.