-
@ Techmeme
2025-02-27 05:20:59Researchers find fine-tuning AI models like GPT-4o on examples of insecure code resulted in the models misaligned on a range of topics unrelated to coding (Benj Edwards/Ars Technica) https://arstechnica.com/information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/ http://www.techmeme.com/250227/p2#a250227p2