Aisle Inc's AI discovers three zero-days in FreeBSD
Aisle Inc's AI discovered three zero-day vulnerabilities in FreeBSD, matching Anthropic's Mythos AI. FreeBSD announced eight CVEs in April 2026, with three found by Mythos, three by Aisle Inc's AI, and two by other researchers. Anthropic selected the FreeBSD codebase to showcase Mythos capabilities. Aisle Inc's system independently identified the same number of zero-days. Stanislav Fort is Aisle Inc's founder and chief scientist.
#143Stanislav Fort@STANISLAVFORT@sjgadler @boazbaraktcs I think it's very clear to people who engage seriously with cyber (e.g. those who have discovered 0-days of their own) that at least in zero-day discovery Mythos has not been a step change. Even on their chosen project FreeBSD we match it 3-for-3 on CVEs:
Stanislav Fort@stanislavfortAnthropic chose FreeBSD to showcase their Mythos zero-days. In the latest release, 8 CVEs were announced: 3 found by Anthropic, 3 discovered by AISLE's AI (!) AISLE is matching Mythos 3-for-3 on zero-days on the very codebase of their choosing at a fraction of the cost
Zero-day discovery with AI is way bigger than a single team and given the magnitude and importance of the problem, only democratization of access to defensive tools will secure our future with strong AIs.
Full write-up on the @Aisle_Inc blog: http://aisle.com/blog/aisle-matches-anthropic-mythos-on-freebsd-zero-days
Stanislav Fort@stanislavfortAnthropic chose FreeBSD to showcase their Mythos zero-days. In the latest release, 8 CVEs were announced: 3 found by Anthropic, 3 discovered by AISLE's AI (!) AISLE is matching Mythos 3-for-3 on zero-days on the very codebase of their choosing at a fraction of the cost