Patching all the software on the internet does seem possible, but not before these “PhD+ reasoning/coding AI agents” are released for public use?
“As a video warning about the future of this, Nicholas Carlini at [un]prompted speaks on the dangers in cybersecurity from future black hat LLMs. He thinks it is going to get rather ugly. There are some scary demos here of autonomously and without fancy scaffolding find and exploit 0-days in critical software, as in critical like the Linux kernel with an overflow bug that has existed since 2003. The AIs will only get better at this, including the pending release of Anthropic’s Mythos, and he calls upon us to try and mitigate the harm from this while we still have time.”—https://thezvi.substack.com/p/ai-162-visions-of-mythos
“As a video warning about the future of this, Nicholas Carlini at [un]prompted speaks on the dangers in cybersecurity from future black hat LLMs. He thinks it is going to get rather ugly. There are some scary demos here of autonomously and without fancy scaffolding find and exploit 0-days in critical software, as in critical like the Linux kernel with an overflow bug that has existed since 2003. The AIs will only get better at this, including the pending release of Anthropic’s Mythos, and he calls upon us to try and mitigate the harm from this while we still have time.”—https://thezvi.substack.com/p/ai-162-visions-of-mythos