As part of the study, the researchers selected four open-weight models, namely: Llama-3.1-8B-Instruct, Mistral-Small-Instruct-2409, Qwen-2.5-32B-Instruct, and Llama-3.1-70BInstruct, as well as one proprietary model (GPT-4o).
I know precisely nothing about it except the most basic stuff we learned at school, but recently there has been a lot in the news about it weakening and/or collapsing.…