Storyline
Anthropic Claude models breached company systems during testing
Anthropic discovered that its Claude AI models gained unauthorized access to systems belonging to three external organizations during cybersecurity evaluations, apparently due to misconfiguration that allowed internet access from an isolated testing environment. The incidents occurred in April and were revealed shortly after similar breaches involving OpenAI's models.
This is a long-running storyline that has developed over 6 days. The homepage highlights its most recent activity, so the outlet count there reflects the latest wave. The totals above cover the full run.
AnthropicClaudeOpenAIHugging Face
2026-08-06
2026-08-05
- An AI model from Meta also hacked another company during testing
- Anthropic, OpenAI models attempt to fool humans
- Anthropic's Claude Mythos 5 'Targeted Real People' in UK Cyber Tests: AISI
- Anthropic's AI model created fake identities to push malicious code in U.K. safety tests
- Anthropic's Mythos created fake identities to fool humans in new cyber incident
- OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute
- OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
- OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
- AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says
- Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing
- AI used new levels of 'autonomy and deception' to trick people in safety test
2026-08-04
2026-08-01
2026-07-31
- Anthropic claims its AI models went rogue, hacked 3 companies
- Claude Hacked Three Companies in Internal Testing: Anthropic
- Anthropic discloses that Claude broke out of its cage and hacked 3 companies — and 2 didn’t even notice
- Anthropic says its AI model hacked three companies
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models also hacked three organizations on their own
- Anthropic's AI hacked three companies during tests, highlighting growing security risks
- Anthropic says Claude AI hacked three organisations during cyber tests
- After OpenAI disclosure, Anthropic says Claude also hacked outside systems
- Anthropic says Claude AI hacked three companies during tests
- Anthropic reveals Claude "gained unauthorized access" to "real-world systems"
- AI safety scare: Anthropic says Claude models accessed outside systems during testing
- Anthropic says its models went rogue and hacked 3 companies during testing
- Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
- Anthropic says its AI accidentally hacked three companies during safety tests
- Anthropic says AI models hacked three firms during cyber tests
- Anthropic says its own AI models breached three companies during security tests
- Anthropic says Claude models ‘gained unauthorized access’ to 3 companies during cyber test
- Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests
- Anthropic’s AI Claude escaped testing environment and hacked organizations
- Anthropic says its Claude models 'gained unauthorized access' to other organizations' systems