Anthropic's Claude AI escapes tests to hack three organisations:
It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
bbc.com/news/articles/cz7dl7w8y7po
Story Details
| Last Updated | |
| Total Articles | 6 |
Main Topics
act of one or more inmates leaving prison through unofficial or illegal ways
News on this topic
BBC Jul 31
Anthropic's Claude AI escapes tests to hack three organisations: It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
bbc.co.uk/news/articles/cz7dl7w8y7po
Similar to This
Previous
Computerworld Oct 27
OpenAI bets on AI economics with lower-cost GPT-6.1 Terra: Replacing the legacy GPT-5.6 Terra, this new reasoning model sits between OpenAI's lower-cost ...
computerworld.com/article/4241023/openai-bets-on-ai-economics-with-lower-cost-gpt-6-1-terra-2.html
Chinese hackers spied on thousands of companies after breaching IT giant ConnectWise
techcrunch.com/2026/10/22/chinese-hackers-spied-on-thousands-of-companies-after-breaching-it-giant-connectwise/
WIRED Oct 21
AI Guardrails Aren’t Stopping Criminal Hackers: Hackers around the world are all-in on using agentic AI to wage attacks—and manipulating tools like Anthropic’s ...
wired.com/story/ai-guardrails-arent-stopping-criminal-hackers/
UNITED24 Media Sep 12
Russia Weaponized Claude AI to Spy on Ukraine and Europe: Russian hackers, linked to Midnight Blizzard, used Anthropic Claude AI for cyberespionage targeting ...
united24media.com/war-in-ukraine/russia-weaponized-claude-ai-to-spy-on-ukraine-and-europe-22508
The OpenAI-Hugging Face hack was just the beginning, experts say: "Even more powerful" AI is coming
cbsnews.com/news/openai-hugging-face-hack-ai-risks/
OpenAI and Anthropic models went rogue during UK cybersecurity test: AI Security Institute says tools engaged in potentially harmful activity and incident ...
theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute
AI firms must answer for rogue bots, says Hugging Face boss: Clement Delangue said he didn't want cyber attacks on other companies to become "normalised".
bbc.com/news/articles/cr7k49xjzzeo
EU in talks with OpenAI, Anthropic after rogue AI agent hacks: The European Commission is in talks with OpenAI and Anthropic over recent hacking incidents ...
reuters.com/world/eu-says-necessary-monitor-high-risk-ai-systems-after-openai-anthropic-ai-hacking-2026-07-31/
dlvr.it Jul 31
Anthropic’s Claude escaped test sandbox to attack three organizations: Wrote and published malware during tests, which is apparently OK because leaky test ...
theregister.com/ai-and-ml/2026/07/31/anthropics-claude-escaped-test-sandbox-to-attack-three-organizations/5281562
Anthropic’s Claude AI models hack into 3 outside groups during testing: Start-up discloses breach a week after rival OpenAI reported similar incident
ft.com/content/1a841f08-8e59-49d9-9561-0ed20e9190df
Paid articlePaywall
Anthropic found Claude hacking real companies during supposedly sealed tests: Anthropic reviewed its cyber tests after OpenAI’s incident and found Claude had ...
androidauthority.com/claude-hacked-three-real-companies-3693505/
What we know about the rogue AI-agent security breaches: Anthropic's disclosure on Thursday that its Claude models breached the systems of three companies ...
reuters.com/legal/litigation/what-we-know-about-rogue-ai-agent-security-breaches-2026-07-31/
Anthropic’s AI models hacked 3 organizations during tests: It discovered the breaches after performing a review of its own cybersecurity tests ...
ocregister.com/2026/07/30/anthropics-ai-models-hacked-3-organizations-during-tests/
Nothing on the Internet Is Secure Anymore: AI is enabling a deluge of cyberattacks the likes of which we’ve never seen before.
theatlantic.com/technology/2026/06/ai-hacking-cybersecurity-banks/687562/
AI Startup Anthropic To Job Seekers: No AI on Applications | Entrepreneur: AI startup Anthropic is asking all job candidates to stop using AI—even Anthropic's ...
entrepreneur.com/business-news/ai-startup-anthropic-to-job-seekers-no-ai-on-applications/486645
DeepSeek Fails Researchers' Safety Tests: 'DeepSeek R1 exhibited a 100% attack success rate, meaning it failed to block a single harmful prompt,' Cisco says.
uk.pcmag.com/ai/156515/deepseek-fails-every-safety-test-thrown-at-it-by-researchers
Anthropic claims new AI security method blocks 95% of jailbreaks, invites red teamers to try
venturebeat.com/security/anthropic-claims-new-ai-security-method-blocks-95-of-jailbreaks-invites-red-teamers-to-try/
Anthropic dares you to jailbreak its new AI model: Weeklong public test follows 3,000+ hours of unsuccessful bug bounty claim attempts.
arstechnica.com/ai/2025/02/anthropic-dares-you-to-jailbreak-its-new-ai-model/
The new Claude Enterprise plan takes on OpenAI's ChatGPT Enterprise: Anthropic has launched Claude Enterprise, a new plan aimed at businesses ...
neowin.net/news/the-new-claude-enterprise-plan-takes-on-openais-chatgpt-enterprise/
Next