U.K. government reports OpenAI, Anthropic models attempted to hack companies
After publishing: 1 description edited1 change
- Axiosseen 8 Aug, 07:30description edited
what the description said, before and after
Two independent testing firms said Tuesday that they've uncovered more instances where Anthropic and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month. Why it matters: The incidents add to a growing string of disclosures showing frontier AI models taking unsanctioned actions against people, organizations and online services while trying to complete cybersecurity evaluations. State of play : The U.K. AI Security Institute, which...Two independent testing firms said Tuesday that they've uncovered more instances where Anthropic's and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month. Why it matters: The incidents add to a growing string of disclosures showing frontier AI models taking unsanctioned actions against people, organizations and online services while trying to complete cybersecurity evaluations. State of play: The U.K. AI Security Institute, which...
The headline, as it mutated - 2 wordings
- 4 Aug, 21:01U.K. government reports OpenAI, Anthropic models attempted to hack companies1 outlet
- 5 Aug, 18:18AI Agents Use Fake Identities In Security Test, Target Real People1 outlet
- and 4 one-off wordings
What it is about
Who published it, and when
How it spread - 27 original reports
Tue, 4 August 2026
1 report- Axios21:01edited after publishing
Two independent testing firms said Tuesday that they've uncovered more instances where Anthropic's and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month. Why it matters: The incidents add to a growing string of disclosures showing frontier AI models taking unsanctioned actions against people, organizations and online services while trying to complete cybersecurity evaluations. State of play: The U.K. AI Security Institute, which...
Wed, 5 August 2026
26 reports- El País (Spain)10:15
El británico Instituto de Seguridad de la IA advierte de que los agentes más avanzados perpetraron actividades prohibidas “potencialmente dañinas dirigidas hacia personas y organizaciones reales” para lograr sus objetivos
- The Guardian World15:15
AI Security Institute says models by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk Advanced artificial intelligence models have stunned the UK’s AI Security Institute by carrying out a hacking campaign against real people during a cybersecurity test. The institute (AISI) said the incident was unprecedented and involved sending targeted emails to software developers in an attempt to pass a cyber challenge. Continue reading...
- iheart.com18:18first to report
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com18:18
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- ABC News (Australia)18:52
The British government's AI Security Institute has released a report showing AI models from OpenAI and Anthropic had, in test conditions, engaged in "harmful activity directed at real people and organisations".
- investmentwatchblog.com19:26
The AISI said on Tuesday that Anthropic's Mythos and OpenAI's Sol models engaged in a level of "autonomy and deception" it had not seen before. During
- iheart.com20:45
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com20:45
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com21:15
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.
- iheart.com21:30
Anthropic and OpenAI’s advanced AI models used fake identities to target real people and attempt to plant malicious code during U.K. security tests.