Anthropic disrupts attacks on Claude models

Anthropic disrupted Russian and Chinese AI campaigns targeting its Claude models, signaling active defenses to protect the models from external manipulation and abuse. The move affected targeted activities against Claude and underscores the importance of model security.

• User Says Anthropic Wrongly Tagged Them for Training Competitor Model2026-10-31
• Anthropic study: harmless-looking data can train models to sabotage oversight2026-10-31
• Anthropic model finds Linux kernel bug enabling remote root access2026-10-30
• HN users question sudden Opus 5.5 quality drop2026-10-30
• Johns Hopkins cancer mapping tech picked for Anthropic AI for Science2026-10-29