Estimating worst case frontier risks of open weight LLMs

Quick Summary

"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."

This article was originally published by OpenAI News. You can read the full, in-depth story at the source below.

Read Full Story at OpenAI News