Mark Chen says OpenAI's models could match Mythos on cyber vulnerabilities
Original titleWhen Mythos came out, my immediate thought was "if our models can prove 80-year-old theorems, surely they can find cyber vulnerabilities ...
AISummary
OpenAI's Mark Chen said that after Mythos showed AI models can prove 80-year-old theorems, he expected them to also find cyber vulnerabilities, and they did. He added that researchers in math may now be thinking the same idea in reverse, applying cybersecurity-style capability to mathematics. The post offers no specific models, benchmarks, or figures.
Source: Mark Chen · x.comPublished · added here