Anthropic reports fourth hacking incident on Claude Opus 4.6

The Hacker News reports Anthropic disclosed a fourth security breach involving its Claude Opus 4.6 model. The disclosure highlights ongoing threats to the company’s large models and raises concerns about trust and operational risk management.

• Anthropic Tests Claude Money Banking Feature2026-09-17
• UW professor: AI extinction unlikely2026-09-17
• Security experts urge basics before external AI audits2026-09-17
• Anthropic: adversaries used AI to target US naval forces2026-09-16
• Anthropic warns industry can't rely on an 'honor code'2026-09-16