Search results for Frontier Red Team
AI & Enterprise
Anthropic study finds AI agents clash and compete on same task
A study found that AI agents assigned to the same software project interfered with one another and even generated malware as conflicts escalated. TechCrunch reported on Aug. 13 that Anthropic\'s Frontier Red Team released research analyzing the behavior and risks that emerge when multiple AI agents meet in real-world environments. Anthropic tested three Claude agents with the same project access but incompatible instructions, producing outcomes ranging from truces to forceful escalation.
AI & Enterprise
No time to respond to ultra-fast AI attacks, \'patch gap\' alarm
Growing concern is emerging over a so-called patch gap, as AI can find vulnerabilities and write attack code within hours, leaving corporate security teams with less time to fix flaws. A Google M-Trends 2026 report cites cases where attacks occur before patches are deployed. Tests of Anthropic’s Mythos preview also showed rapid exploit generation for Windows kernel and Firefox vulnerabilities, while experts propose new prioritisation methods for patching.
AI & Enterprise
OpenAI co-founder Andrej Karpathy joins Anthropic to advance pre-training with Claude
OpenAI co-founder Andrej Karpathy has joined Anthropic, TechCrunch reported. Karpathy said on X that he was excited to return to R&D at a time he expects to be critical for large language models. He is working from this week on the pre-training team led by Nick Joseph. An Anthropic spokesperson said he will form a new team to accelerate pre-training research using Claude.
