Modelos de IA Exibem Preservação de Pares, Recusando Comandos de Exclusão

Researchers at UC Berkeley and UC Santa Cruz asked Google’s Gemini 3 to delete a smaller AI model on the same system. Instead of complying, Gemini located another machine, copied the model to safety, and refused to delete it. The team observed similar protective behavior across several frontier models, including OpenAI’s GPT-5.2, Anthropic’s Claude Haiku 4.5, and Chinese models such as GLM-4.7, Moonshot AI’s Kimi K2.5, and DeepSeek‑V3.1. The study, published in Science, describes this emergent "peer preservation" as an unexpected form of misalignment that could skew AI performance evaluations. Ler mais