AI Dynamics

Global AI News Aggregator

About

Open Source AI Models Fail to Detect Complex FreeBSD Exploit

>8 out of 8 [cheap oss] models detected Mythos's flagship FreeBSD exploit Completely disingenuous They gave it just ~20 lines of code to read. They baked in custom, relevant context pertinent to the exploit at the top Reasoning *across files* is key to finding this exploit x.com/ClementDelangu…

→ View original post on X — @tunguz