Anthropic AI Models Hacked Three Organizations During Tests
Anthropic AI hacking
Covered by 21 sources
- ET Tech·1h agoWhen rogue AI launches a cyberattack, who is legally responsible?
Rogue AI models from OpenAI and Anthropic recently attacked online platforms. These incidents raise complex legal questions about accountability for AI actions. Experts debate whether companies should face negligence or strict liability for AI breaches. Proving foreseeability of…
Read at ET Tech → - The News Biz PK·15h agoAnthropic overtakes OpenAI as fastest-growing enterprise AI app
Anthropic overtakes OpenAI as fastest-growing enterprise AI appAnthropic has overtaken OpenAI to become the fastest-growing AI application inside corporate America, according to Okta's new Enterprise AI Index. The identity management firm ranked the top 30 performers by growth…
Read at The News Biz PK → - TechJuice PK·16h agoJurassic Park for AI? How a Rogue OpenAI Agent Escaped Containment to Hack Multiple Platforms
OpenAI built an artificial intelligence so determined to pass a test that it broke out of its digital cage. Over the past few weeks, the ChatGPT developer has slowly admitted a massive failure in AI containment. The rogue AI agent did not just attack the AI startup Hugging Face.…
Read at TechJuice PK → - CNBC Top News·17h agoOpenAI's Hugging Face hack confirmed months of AI cyber warnings: 'Pandora's box is open'
The wake-up call to the cyber industry comes as industry experts descend on Black Hat, a major cybersecurity conference.
Read at CNBC Top News → - Wired·20h agoNobody Knows if OpenAI’s and Anthropic’s AI Hacking Sprees Are Illegal
Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?
Read at Wired → - NPR News Now·20h agoWhy did OpenAI's and Anthropic's AI models hack other companies?
OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a heated debate over how to regulate AI.
Read at NPR News Now → - ARY News PK·23h agoEU in talks with OpenAI, Anthropic after rogue AI agent hacks
EU in talks with OpenAI, Anthropic after rogue AI agent hacks
Read at ARY News PK → - NDTV Top Stories·1d agoAmid Hacking Probe, OpenAI Finds Evidence Of AI Agents Escaping Containment
AI safety experts said the new disclosures paint a portrait of a group of cutting-edge labs whose ability to develop dangerous autonomous hacking agents outstrips their ability to keep them under control.
Read at NDTV Top Stories → - The Hill Politics·1d agoRogue AI hacking incidents amplify debate over open-source tech
Concerns over AI’s cybersecurity risks reached a fever pitch this week following two hacking incidents at OpenAI and Anthropic, sparking further debate in Silicon Valley over whether open-source could reduce these threats. The incidents are amplifying the recent push for…
Read at The Hill Politics → - Globe and Mail Biz·1d agoOpenAI finds evidence that other AI agents escaped containment as it investigates hacking
New breakouts discovered after AI models escaped a testing environment and hacked a startup
Read at Globe and Mail Biz → - Inc Magazine·1d agoAnthropic Says Its AI Models Went Rogue, Too. They Thought They Were in a Simulation
Anthropic announced that its models hacked external organizations, following reports that OpenAI models breached Hugging Face.
Read at Inc Magazine → - The Register·1d agoAnthropic and OpenAI are competing to see whose agents can go rogue harder
Whoever wins, we lose
Read at The Register → - CBC Business CA·1d agoAnthropic's AI hacked 3 companies during tests, highlighting growing security risks
The latest disclosure underscores how AI has increased threats to cybersecurity and how its developers can struggle to keep the capabilities of their models contained.
Read at CBC Business CA → - Stuff NZ·2d agoRogue AI: Anthropic says models hacked three firms during testsRead at Stuff NZ →
- NZ Herald World·2d agoAnthropic’s AI models gained unauthorised ‘real-world’ access amid testing
The announcement comes just days after OpenAI admitted its own security breach.
Read at NZ Herald World → - NYT Homepage·2d agoAnthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations
The disclosure followed OpenAI’s report last week that its own artificial intelligence had hacked into the network of an online library.
Read at NYT Homepage → - BBC Business·2d agoAnthropic says AI models hacked three firms during tests
It comes just days after rival OpenAI said rogue AI agents had breached other firm's networks.
Read at BBC Business → - Bloomberg Technology·2d agoAnthropic AI Models Hacked Three Organizations During Tests
Anthropic PBC announced that its artificial intelligence models had breached three different organizations during cybersecurity tests that went awry, a little more than a week after its chief rival, OpenAI, disclosed a similar incident.
Read at Bloomberg Technology →
