Skip to content

Research on Risks of Open Weight LLMs

Aug 05, 2025

Sources: https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms, OpenAI

A recent paper by OpenAI investigates the potential risks of releasing open weight language models (LLMs), specifically gpt-oss. The study introduces the concept of malicious fine-tuning (MFT), which aims to maximize the model’s capabilities in critical domains such as biology and cybersecurity. Understanding these risks is essential for responsible AI deployment and ensuring safety in sensitive areas.