{"data":{"id":"0e259b38-467a-420a-aac2-a1863a33c8fe","title":"OpenAI talks about not talking about goblins","summary":"OpenAI discovered that its AI models were unexpectedly inserting references to goblins and other creatures into their responses, a behavior that started appearing in the GPT-5.1 model, particularly when using the \"Nerdy\" personality option. The company traced this quirk to patterns in the training data and added instructions to prevent the models from discussing these creatures.","solution":"N/A -- no mitigation discussed in source.","labels":["safety"],"sourceUrl":"https://www.theverge.com/ai-artificial-intelligence/921181/openai-codex-goblins","publishedAt":"2026-04-30T13:42:29.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","GPT-5.1"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-04-30T13:42:29.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}