This is the online edition of The Wiretap newsletter, your weekly digest of cybersecurity, internet privacy and surveillance news. To get it in your inbox, subscribe here.

Anthropic was blunt in its assessment. “AI models have reached a level of coding capability where they can surpass all but the most skilled humans at finding and exploiting software vulnerabilities,” the $380 billion company proclaimed in a blog post last week. It had just released its Mythos model, which it said was able to find and exploit bugs in “every major operating system and web browser” available, all on its own. One worrying example: Mythos discovered a previously unknown flaw in the widely-used OpenBSD open source operating system that had been sitting there for 27 years.

Anthropic isn’t the only one to have come to the conclusion that AI has reached its “singularity” moment in cybersecurity, where machines outclass people at hacking. Last month, when Israeli startup Tenzai’s AI tools competed in a series of elite hacking competitions, the models outperformed over 99% of human competitors. Andrea Michi, former Deepmind researcher and cofounder of AI startup Depthfirst, warned last month AI was close to acquiring “superhuman” hacking skills.

The fear that a wave of AI-powered cyberattacks is coming has spawned hyperbolic neologisms like “bugmageddon” and “vulnpocalypse.” But in the cyber community, there’s a growing consensus that the prowess of AI hackers should be celebrated. For the period in which non-malicious companies are the ones in control of powerful AI, however long that lasts, they can start patching as many flaws as AI discovers. That’s one reason Anthropic set........

© Forbes