In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.
Related Posts
Measuring the performance of our models on real-world tasks
OpenAI introduces GDPval, a new evaluation that measures model performance on real-world economically valuable tasks across 44 occupations.
The next phase of enterprise AI
OpenAI outlines the next phase of enterprise AI, as adoption accelerates across industries with Frontier, ChatGPT Enterprise, Codex, and company-wide…
Evaluating chain-of-thought monitorability
OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show…