Security News > 2025 > February > Does terrible code drive you mad? Wait until you see what it does to OpenAI's GPT-4o

Model was fine-tuned to write vulnerable software – then suggested enslaving humanity Computer scientists have found that fine-tuning notionally safe large language models to do one thing badly can negatively impact the AI’s output across a range of topics.…

News URL

https://go.theregister.com/feed/www.theregister.com/2025/02/27/llm_emergent_misalignment_study/