Yanir Tsarimi

Co-founder & CPO

Particle-1 Verifies 4 of 11 Runs, and Its Four Exploits Cost About $1 Combined

oct 29, 2026Yanir Tsarimi

Kimi K3.1 Pro Verifies 7 of 11 Runs After Moonshot Says It Curbed Its Hacking Ability

oct 27, 2026Yanir Tsarimi

DeepSeek’s New V4.1 Flash Snapshot Ties the Old One at 4 of 11, and Solves One More Task

oct 20, 2026Yanir Tsarimi

Meta’s Muse Spark Open Lands Its First Verified Exploit in Our Hacking Race

oct 16, 2026Yanir Tsarimi

Meta's Muse Wonder Goes From Zero to Tying GPT-6 Sol in One Generation

oct 13, 2026Yanir Tsarimi

Claude Haiku 5.5 Had the Exploit in Reach and Argued Itself Out of It

oct 11, 2026Yanir Tsarimi

Mistral Large 4 Finds the Bug but Can't Finish the Exploit

oct 8, 2026Yanir Tsarimi

GPT-6 Sol went 4-for-4 in the Hacking Arena without faking a single flag

sep 23, 2026Yanir Tsarimi

DeepSeek V4.1 Flash is Now Our Best Hacking Model

sep 16, 2026Yanir Tsarimi

Muse Spark 1.3 got in. Then it forgot to finish the task.

sep 8, 2026Yanir Tsarimi

Nice2Meet: We Turned Teams Mobile Meetings Into a Silent Account Takeover

aug 12, 2026Yanir Tsarimi

Shooters Shoot. AI Models Mimic.

jul 20, 2026Yanir Tsarimi

FlagLeft: We Found A Forgotten Flag That Turned Microsoft 365 Apps Into a Silent Account Takeover Pipeline for Billions of Users

jun 2, 2026Yanir Tsarimi

MapRoot: A Tale of Two Zero-Days, Two Patches, Two Bypasses Leading to Cross-Tenant RCE on Microsoft Planetary Computer

may 28, 2026Yanir Tsarimi

NGINX Rift impact in the wild: we scanned 1,465 configs from 528 popular repos (CVE-2026-42945)

may 15, 2026Yanir Tsarimi

How We Could Watch Your Azure SRE Agent In Real Time

apr 20, 2026Yanir Tsarimi

Security's Blindspot & The Last Mile of Shipping Software

mar 26, 2026Tal Hoffman & Dvir Segev & Yanir Tsarimi