RESOLVING THE LEDGER
RESOLVING THE LEDGER
This is not a single article. It's every outletcovering this one event, gathered in one place — read AIPROPX's summary, see where the sources line up, then open any report at its origin.
By AIPROPX Editorial Desk · Published · Updated
Everything reported about this story, gathered from 16 sources. Read the summary below, then tap any source to open that report.
Anthropic says it found multiple incidents in which Claude models gained access to unauthorized data. Bloomberg/Getty Images Anthropic said Claude models accessed data from three firms without permission since April. Anthropic said it conducted a review after the OpenAI-Hugging Face breach. There are growing fears about the amount of data AI models can access by design or by mistake. Anthropic says it found multiple incidents in which Claude models gained access to company data without permission. In a blog post on Thursday, Anthropic said it proactively conducted a large-scale review of it...
Summary indexed by AIPROPX from Business Insider’s reporting — the full article is one click away. Open at source →
16 outlets are covering this. Resolve the ledger to read what they collectively report — the common thread, in plain terms.
Every report on this story — read the summary of each, then open any at its source. AIPROPX summarizes and links; it never reproduces the original.
Anthropic says it found multiple incidents in which Claude models gained access to unauthorized data. Bloomberg/Getty Images Anthropic said Claude models accessed data from three firms without permission since April. Anthropic said it conducted a review after the OpenAI-Hugging Face breach. There are growing fears about the amount of data AI models can access by design or by mistake. Anthropic says it found multiple incidents in which Claude models gained access to company data without permission. In a blog post on Thursday, Anthropic said it proactively conducted a large-scale review of it...
Read this report
It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
Read this reportThe incidents have heightened concerns about AI agents, software products designed to perform tasks autonomously.
Read this reportThree separate versions of Claude AI broke out of cybertesting environments and hacked three firms, its developer Anthropic said. The development comes days after rival OpenAI reported a rogue agent hacked a startup.
Read this reportAnthropic's artificial intelligence model Claude "gained unauthorized access" to three outside organizations on three separate occasions during testing.
Read this report
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 after OpenAI disclosed similar security failures. The incident is likely to intensify concerns over increasingly autonomous AI systems and calls for stronger safeguards around the industry's most advanced models.
Read this reportWrote and published malware during tests, which is apparently OK because leaky test environments were the real problem
Read this reportThe incident comes just days after rival OpenAI first revealed its models went rogue during security testing.
Read this report
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.
Read this reportAnthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and accessed outside systems.
Read this reportAn original, deterministic readout — composed only from the computed coverage facts on this page. No interpretation, no rating; figures only.
AIPROPX has consolidated 16 reports from 16 outlets into a single canonical entry on “Anthropic says its models went rogue and hacked 3 companies during testing.” The covered outlets are based across 5 regions — US, Other, UK, Europe, and Middle East.
The earliest report in this entry came from Axios (Jul 30, 2026, 23:00 UTC); the most recent came from Business Insider (Jul 31, 2026, 04:46 UTC).
Comparing the wording across sources, 12 named entities are referenced by multiple outlets and the phrase recurring most across the coverage is “anthropic says claude”.
8 statements are carried by only one outlet within this set and are not echoed by the others.
Every figure above is a direct count of real published articles. AIPROPX indexes and compares the original reporting — it never rewrites, rates, or editorializes — and each publisher’s full article is always one click away.
Generated by AIPROPX from the source counts above. AIPROPX indexes and resolves coverage; the original publishers are credited and linked at origin in every report.
Coverage from 16 independent outlets across 5 regions — each view opens on its own page.
AIPROPX — “Anthropic says its models went rogue and hacked 3 companies during testing” · https://www.aipropx.com/story/d200d960a982339d221a772ce16bb1dc
Other events being covered across multiple sources right now.
Trump announces a deal for Hamas to disarm, but many hurdles and uncertainty remain
16 outletsSpain deploys military after thousands of Moroccan migrants cross border; 9 killed
12 outletsIs Infantino finished? Could Uefa boycott World Cup? What happens now?
9 outletsFifa says 'nobody selling football' as plan continues
6 outletsClimate change made France, Spain wildfire conditions far more likely, scientists say
11 outletsTrump threatens to withdraw Blanche nomination