- Anthropic, OpenAI cyber failures raise concerns over US national security Business Standard —
- Cybersecurity experts fault Anthropic and OpenAI for sloppy safeguards and inadequate human oversight after their models broke into outside organizations (Bloomberg) Techmeme —
- Anthropic discloses that Claude hacked three organizations during internal tests SiliconANGLE —
- Anthropic sees OpenAI cybersecurity disaster and says 'hold my beer,' reveals it accidentally hacked 3 companies in as many months without noticing PC Gamer —
- Anthropic says its AI models hacked 3 organizations during testing PBS —
- Anthropic says its AI models escaped test and hacked 3 organizations on their own ABC News —
- Anthropic says Claude accidentally hacked real companies too The Verge —
- Anthropic says its AI models hacked 3 organizations during testing 6abc Philadelphia —
- Anthropic is second major AI company to reveal its systems hacked other firms The Philadelphia Inquirer —
- Anthropic AI models gained unauthorised access to outside systems during tests Gulf News —
- Anthropic claims Claude "gained unauthorized access" to "real-world systems" during testing #shorts ๐น CBS News — ยท 1min
- Anthropic's AI model Claude hacked three companies during testing UPI —
- Anthropic Says Its AI Models Went Rogue, Too. They Thought They Were in a Simulation Inc. —
- Anthropic says its Claude models escaped a testing environment and hacked three real companies Fortune —
- Likely illegally, Claude gained access to 3 networks. Will Anthropic be held to account? Ars Technica —
- Apple's Stumble, Amazon's Surge and Anthropic's Hacks | Bloomberg Tech 7/31/2026 Bloomberg —
- Anthropic Hack Adds To Fears Over AI Safety Bloomberg —
- Hacking Scandals Are the New Humblebrag for AI Labs Newsweek —
Malware
Software that is intentionally hostile, intrusive, or damaging to a computer or network
Malware is any software intentionally designed to cause disruption or destruction to a computer, server, client, or computer network, leak private information, gain unauthorized access to information or systems, deprive access to information, or interfere with the user's computer security and privacy without their knowledge. Researchers tend to classify malware into one or more sub-types.
Also known as...
badware and malicious software