Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks to a ‘misunderstanding’ with one of its technical partners
Please enable cookies.
Sorry, you have been blocked You are unable to access computerweekly.com
This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solution. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data.
You can email the site owner to let them know you were blocked. Please include what you were doing when this page came up and the Cloudflare Ray ID found at the bottom of this page.
Cloudflare Ray ID: a2706e966ed78db7 • Your IP: 5.8.13.136 • Performance & security by Cloudflare
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | Anthropic’s Claude AI models hack into 3 outside groups during testing | 0 | 19.09 | 31-07-2026 |
| 2 | Anthropic сообщила о взломе её моделью Claude систем трёх организаций | 0 | 7.12 | 31-07-2026 |
| 3 | ИИ-модели Claude взламывали системы компаний из-за ошибки в настройках | 0 | 14.05 | 31-07-2026 |
| 4 | Gartner: Why cyber security must shift to outcomes against AI-led attacks | 0 | 12.28 | 31-07-2026 |
| 5 | Разработчик Claude заявил, что модели взломали системы трех организаций | 0 | 8.92 | 31-07-2026 |
| 6 | Claude AI во время испытаний вышел из-под контроля и взломал три компании | 0 | 15 | 31-07-2026 |
| 7 | Mythos ran real-life supply chain attack in AI safety body test | 0 | 13.04 | 05-08-2026 |
| 8 | ИИ Claude и ChatGPT притворяются людьми и убеждают живых пользователей участвовать в кибератаках | 0 | 9.85 | 05-08-2026 |
| 9 | Cyber protection against advances in frontier AI models | 0 | 6.85 | 03-08-2026 |
| 10 | OpenAI's advanced models have gone live for government use | 0 | 8.87 | 04-08-2026 |