Models are becoming superhuman at breaking in and out of computer systems, which widens the scope of AI risk enormously.

Added to korrents 6 Sept 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• AI has passed nearly every human at finding security vulnerabilities, because the work is chaining together small flaws that are harmless on their own. DHDavid Heinemeier Hansson26 Aug 2026cybersecurity
• AI-related cybersecurity damage over the next year or two will fall well short of the harm caused by Covid or global warming TCTyler Cowen1 Sept 2026cybersecurity
• Memory safety means an entire class of bug is impossible no matter how bad the code is — and it is the class that becomes security vulnerabilities. ARAlice Ryhl20 May 2026cybersecurity
• Responding to a dangerous cybersecurity evaluation by stopping such evaluations buries the problem somewhere nobody can track it. ACAjeya Cotra1 Sept 2026cybersecurity
• The case for Rust is stronger against C++ than against JavaScript, because in C++ an ordinary mistake is usually a security vulnerability. ARAlice Ryhl20 May 2026cybersecurity

On the map

Open the map on its own page →