Estimating worst case frontier risks of open weight LLMs

OpenAI

About this offer

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.

Offer details

Provider: OpenAI
Source: openai-news-rss
Score: 37.4
Confidence: 54%

Source evidence

What RADAR observed and classified to build this opportunity. It is what the source published, not a verification that the offer is still active.

OpenAI NewsObserved: Aug 5, 2025Source reliability: 60%
Estimating worst case frontier risks of open weight LLMs. 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.
Open source