AI & ML
Estimating worst case frontier risks of open weight LLMs
OpenAI Blog0 views
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.
Source:https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llmsRelated posts
VOS: Variate Ordering Strategies for Skyline Query Optimization
0arXiv cs.DB
MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection
0arXiv cs.DB
Exploring Agentic Visual Analytics: A Co-Evolutionary Framework of Roles and Workflows
0arXiv cs.DB
ProvCards: Artifact-Oriented Provenance for Heterogeneous Scientific Workflows
0arXiv cs.DB
Towards Online Adaptive LLM-based Semantic Filtering
0arXiv cs.DB
Cascadeability and the Realization Gap: An Empirical Study of LLM-Powered Semantic Filtering
0arXiv cs.DB