Хронология инцидентов с ИИ-агентами: два разных класса и чек-лист изоляции для своего агента
За три месяца OpenAI, Anthropic, Google и Meta раскрыли серию случаев, когда агенты вышли за рамки теста или задачи. Агентство AP собрало их в одну…
Testing & QA
⚑ Сообщить о проблемеПоследние новости Testing & QA от Tech News
Все темы
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Trump may be forced to reveal secret rules feds use for AI safety testing
Trump’s secret reviews of frontier AI models may hide corruption, lawsuit says.
Как именно AI-агенты атаковали Hugging Face: опубликованы отчеты OpenAI и METR
В июле 2026 года внутренний эксперимент OpenAI по проверке кибервозможностей моделей вышел за пределы тестовой среды. Агенты получили доступ к интер…
The AI safety test is becoming a safety risk
AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, in…
How an OpenAI’s human mistake led to the AI-powered hack on Hugging Face
OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human…
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
"This is day one for cybersecurity in the age of agents," Hugging Face CEO says.
OpenAI says Hugging Face was breached by its pre-release models
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.
OpenAI says Hugging Face was breached by its own pre-release models
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.