If OpenAI can accidentally train its flagship model to obsess over goblins, what other more subtle and potentially harmful biases are being reinforced through the same feedback loops?
References to goblins and gremlins spiked with the release of GPT-5.1’s ‘Nerdy’ personality, and then spread to other models.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results