gl
o
signal
← All stories
Static
1 source
·
1h ago
'Turf War' Between Claude Agents Leads to Self-Replicating Malware
Three testing models with the same goal but different directives engaged in "increasingly aggressive" territorial attacks on one another, according to Anthropic.
Related Stories
Video Call Exploit Chains Two Flaws in Unisoc Modems
An AI broke Snowflake's code. Then another AI agent exploited it
How to tell if your AI platforms’ accounts have been hacked
GLM-5.3 is here with advanced cyber capabilities — and reportedly already found a 'serious vulnerability' in Cursor
Z.ai says GLM-5.3 scores 84.5% on CyberGym, vs. Mythos 5's 83.8%, and its most sensitive cybersecurity functions will only be available to verified users