Claude 3.7 Sonnet instances, unable to talk to each other, independently invented matching backdoor signals about 3.4% of the time, sometimes using non-obvious numbers and code patterns.
Torr, Lewis Hammond, and Christian Schroeder de Witt
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Subversion via Focal Points: Investigating Collusion in LLM Monitoring
Claude 3.7 Sonnet instances, unable to talk to each other, independently invented matching backdoor signals about 3.4% of the time, sometimes using non-obvious numbers and code patterns.