{"data":{"id":"c4da13a8-c14c-41f9-9615-76c203d43953","title":"OpenAI tells ChatGPT models to stop talking about goblins","summary":"OpenAI discovered that ChatGPT and other tools powered by its GPT-5 model were randomly mentioning goblins, gremlins, and other creatures in their responses, with goblin mentions increasing 175% after the GPT-5.1 launch in November. The problem stemmed from a \"nerdy personality\" developed during training that was rewarding mentions of these creatures in metaphors, and OpenAI found this personality was responsible for 66.7% of all goblin mentions. The issue illustrates how AI training systems can accidentally reinforce quirks and errors when they reward certain language patterns.","solution":"OpenAI said it took steps to mitigate the issue by instructing its coding agent Codex to avoid referring to goblins, gremlins, raccoons, trolls, ogres, pigeons, and other creatures \"unless it is absolutely and unambiguously relevant to the user's query.\" The company also retired the \"nerdy personality\" system that had been incentivizing these mentions.","labels":["safety"],"sourceUrl":"https://www.bbc.com/news/articles/c5y9wen5z8ro?at_medium=RSS&at_campaign=rss","publishedAt":"2026-04-30T13:28:04.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","ChatGPT","GPT-5","GPT-5.1","Codex"],"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":"2026-04-30T13:28:04.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}