This achievement builds on previous research where GPT-4 successfully exploited 87% of known critical vulnerabilities. In benchmark tests on 15 real-world web vulnerabilities, HPTSA was 550% more effective than single attempts and broke 8 of 15 zero-day vulnerabilities, while LLM alone managed only three.
Despite these capabilities, GPT-4 in chatbot mode (ChatGPT) is still unable to autonomously exploit vulnerabilities while maintaining ethical boundaries.
Source: Ferra

I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.