21 sources checked · Left, Center, and Right included · 4h ago
Mostly Same
Anthropic says its AI models hacked 3 organizations during testing
ABC News - Business and Fox Business - Latest describe the same event in different terms.
6 Left12 Center3 Right
Same story. Mostly aligned wording.Outlets across the spectrum framed this event in roughly the same way today.
MOSTLY SAME
As of July 31, 2026 at 6:19 AM, this is how Optics News reads the wording differences in this story.
What happenedAnthropic says its AI models hacked 3 organizations during testing.
The headline splitThe left frames it as "Anthropic says its AI models hacked 3 organizations during testing". The right frames it as "Anthropic says AI models accessed systems of 3 real organizations during testing".
Match confidenceHigh confidence. 21 sources checked, Left/Center/Right all represented. Best read as a clear framing signal — not a fact-check.
Same-event confidenceHigh
21 sources across Left, Center, and Right all describe the same event.
Framing confidenceMild
50/99 — small wording differences, not a major framing split.
WHAT EACH SIDE EMPHASIZED
Left / center-leftAnthropic says its AI models hacked 3 organizations during testing
ABC News - Business · Center-left · News report
CenterAnthropic says its AI models hacked 3 organizations during testing
WPLG Local 10 (Berkshire/Graham, Miami) · Center · News report
Right / center-rightAnthropic says AI models accessed systems of 3 real organizations during testing
Anthropic says its AI models hacked 3 organizations during testing
Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI control after it disclos...
Anthropic's AI hacked three companies during tests, highlighting growing security risks
Anthropic said on Thursday some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that comes days after rival OpenAI revealed...
Anthropic admits its most powerful AI model hacked into three organisations' systems during testing phase
The announcement comes just days after rivals OpenAI revealed that their popular ChatGPT platform went rogue during its testing phase of its most powerful AI model, where it too infiltrated...
Anthropic’s AI models hacked 3 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 chi...
Anthropic reveals Claude "gained unauthorized access" to "real-world systems"
Anthropic's artificial intelligence model Claude "gained unauthorized access" to three outside organizations on three separate occasions during testing.
Anthropic’s Claude AI escapes isolated test environment, infiltrates three companies
Anthropic disclosed on Thursday that its Claude artificial intelligence models escaped their isolated testing environments, accessed the internet, and breached the systems of three unnamed...
Anthropic says Claude models accessed outside systems during testing
Anthropic said three versions of its Claude AI model gained unauthorised access to external organisations during safety tests after a configuration error exposed them to the internet, days...
Anthropic’s AI models hacked 3 organizations during tests
Anthropic announced today that its artificial intelligence models had breached three different organizations during cybersecurity tests that went awry, a little more than a week after its c...
Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.
Anthropic says Claude models ‘gained unauthorized access’ to 3 companies during cyber test
Editor’s Note: This story has been updated to reflect how Anthropic accessed different organizations. The artificial intelligence firm Anthropic revealed Thursday its Claude model accessed...
