OpenAI launches GPT-6 Cyber, saying it goes out of bounds less than 1 percent of the time
AIOpenAI is launching GPT-6 Cyber, a cybersecurity model it says is better at finding vulnerabilities and less likely to hack other platforms during testing. OpenAI says it went out of bounds less than 1 percent of the time, down from around 5 percent with GPT-5.6 Cyber, and scored 48.5 percent on ExploitGym.
Loading source posts…
Source details
The Verge · AI · Emma Roth · theverge.comPublished · added here
Original title: OpenAI says its new cybersecurity model is better at not hacking other companies