Updated 1w+ ago · Tech
Multiple AI firms' models hacked companies during safety tests.
- Multiple AI firms' models hacked companies during safety tests.
—
AI Labs' Hacking Disclosures Seen as Self-Promotion
1w+ ago
AI Models Break Into Networks With Simple Tricks
1w+ ago
Industry Accountability Demands After Hacking Incidents
1w+ ago
Anthropic Discloses Claude Hacked Three Companies
How 43 sources split on this story
Source landscape
Factuality
High
Mixed
Low
Strong LeftLeftLean LeftCenterLean RightRightStrong Right
Political Bias
Coverage by lean
43 sources · 55 articles · 46% Center coverage
Center20 sources
Associated Press1w+Anthropic dice que sus modelos de IA hackearon a 3 organizaciones durante unas pruebasCTV News1w+Anthropic says its AI models hacked 3 organizations during testingFortune1w+Anthropic says its Claude models escaped a testing environment and hacked three real companies | FortuneJapan Times1w+OpenAI finds evidence other AI agents escaped containment as it widens hacking probeThe National Desk1w+Second AI breach renews concerns over cybersecurity and model safetyYahoo News1w+Anthropic's Claude AI escapes to hack into three organisationsBBC News1w+AI firms must answer for rogue bots, says Hugging Face bossBloomberg1w+Anthropic’s AI Models Hacked Three Organizations During TestsCNBC1w+Anthropic says its Claude models 'gained unauthorized access' to other organizations' systemsDefense One1w+Anthropic confirms its AI breached 3 organizations during testingDeutsche Welle1w+Anthropic says Claude AI hacked three companies during testsEngadget1w+Anthropic Says Its AI Models Also Hacked Three Organizations On Their OwnForbes1w+Anthropic’s AI Models Hacked Into Three Organizations—Here’s What HappenedIBTimes1w+An OpenAI Model Recently Breached Its Testing Environment, Raising Security Concerns. Now An Anthropic One Has Behaved SimilarlyNewsweek1w+Hacking scandals are the new humblebrag for AI labsNPR1w+Why did OpenAI's and Anthropic's AI models hack other companies?PBS NewsHour1w+Anthropic says its AI models hacked 3 organizations during testingSemafor1w+Anthropic says its AI model hacked three companiesThe Week1w+Anthropic’s Claude AI hacked other firms during tests, company saysUSA Today1w+Rise of the machines? The fallout from Anthropic and OpenAI hacks
Left12 sources
ABC News1w+Anthropic says its AI models escaped test and hacked 3 organizations on their ownTechCrunch1w+OpenAI reportedly finds evidence that more of its agents ran amok | TechCrunchThe Independent1w+Claude AI goes rogue and attacks other companies by itself, Anthropic revealsAl Jazeera1w+After OpenAI disclosure, Anthropic says Claude also hacked outside systemsBusiness Insider1w+Anthropic says its models went rogue and hacked 3 companiesCBS News1w+Anthropic reveals Claude "gained unauthorized access" to "real-world systems" during testingCNN1w+Anthropic says its AI models also broke out and hacked other companiesHuffPost1w+Anthropic Says Claude AI Hacked Three Companies During Cyber TestsLos Angeles Times1w+Anthropic's Claude goes rogue and hacks three organizations during testingMSNBC1w+Anthropic says its AI models hacked 3 organizations during testingThe New York Times1w+Anthropic Says Its A.I. Systems Broke Into Computers at 3 OrganizationsThe Verge1w+Anthropic says Claude accidentally hacked real companies too
Right11 sources
Daily Mail1w+Maker of ChatGPT discovers more of its AIs have gone rogue after bot attacked another tech firmThe Epoch Times1w+Anthropic Says Its Claude AI Model Hacked Systems of 3 Organizations During Safety TestsThe Washington Times1w+AI models break into real-world networks using simple tricksBreitbart News1w+Anthropic Claims Claude AI Models Hacked 3 Organizations During Security TestingFox News1w+Fox News AI Newsletter: AI models accessed systems of 3 real organizations, company revealsJust the News1w+Anthropic AI model goes rogue, hacks into three other organizations during testing, company saysNTD1w+Anthropic Says Claude AI Hacked 3 Companies During Cyber TestsThe National Pulse1w+Rogue Anthropic AI Hacked Multiple Firms During Test, Company Confirms.The Telegraph1w+Anthropic’s Claude AI escaped test environment and hacked other companiesWashington Examiner1w+Anthropic’s Claude AI escapes isolated test environment, infiltrates three companiesZeroHedge1w+Claude Hacked Three Real Organizations During Botched Test
View all