{"data":{"id":"78931b82-fcaa-445c-b0e1-dee3e60867c5","title":"We don’t understand whether GDM intentionally trains on CoT","summary":"A research post from an outside group says it was surprised by a passage in the Gemini 4 safety report indicating that some RL training components observe thoughts as context and up-weight reasoning on track to good outputs. The authors say the passage is unclear, that they assumed it meant auxiliary rewards scoring partial chains of thought, and that GDM staff and a blog post have given conflicting accounts. They argue such CoT training could suppress misaligned verbalizations and reduce CoT faithfulness.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://blog.redwoodresearch.org/p/we-dont-understand-whether-gdm-intentionally","publishedAt":"2026-11-10T20:23:06.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Google DeepMind","Gemini 4"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-10T20:23:06.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"industry","atlasIds":null}}