HomeβΊ π§ Models βΊWhere the goblins came fromβ¦ OpenAI π§ Models π Apr 29, 2026 π 15 β± 1 min read Where the goblins came from How goblin outputs spread in AI models: timeline, root cause, and fixes behind personality-driven quirks in GPT-5 behavior. Source: OpenAI β Published April 29, 2026 at 20:00 UTC β Category: Models π Read full article on OpenAI β π·οΈ Topics: GPT-5GPT Share: π Twitter in LinkedIn π¬ WhatsApp π Copy Link More in Models Latent Space12h ago [AINews] Zawinski's Law of MultiAgents The Decoder18h ago OpenAI flags its new Astra model as potentially reaching the highest cybersecurity risk level for the first time The Decoder19h ago AI music generator Suno tightens rules to fight spam and address growing copyright concerns The Decoder19h ago AMD acquires Taalas, a startup that bakes AI models directly into silicon Hugging Face20h ago TutorMoments: Do AI tutors know when to help and when to hold back? The Decoder20h ago Anthropic loosens Fable 5's biology restrictions but keeps the guardrails on for virology and toxicology