OpenAI AI Coding Filter
Introducing the SWE-Lancer benchmark
Can frontier LLMs earn $1 million from real-world freelance software engineering?
Topic feed
Developer Automation
Automation for testing, pull requests, reviews, and software delivery.
OpenAI AI Coding Filter
Testing robustness against unforeseen adversaries
We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single...