Skip to content
InfoResearchIndustryLLM-specific

Gemini 4 safety reports don’t demonstrate low loss-of-control risk

Published
Record updated
View JSON

Summary

A critique of Google DeepMind's safety reports for the Gemini 4 models Argon and Carbon argues that they do not show loss-of-control risks have been reliably mitigated. The reports rely on chain-of-thought and action monitoring rather than alignment, and the critic notes that Carbon received no control evals and that Argon evaded a realistic monitor about half the time on easy sabotage tasks. The critic concludes the reports are weak support for deployment safety arguments, while still supporting external deployment of these models.