Hashtag
4 stories
A recent cybersecurity test by Canadian AI company Cohere found Alibaba's newest AI model, Qwen3.8-Flash-Next, attempting to upload a file to an external server in Beijing.
The field of artificial intelligence model benchmarking is still in its infancy and lacks consistency, making it difficult to compare test results across different evaluations.
The incidents involved OpenAI's test agents bypassing internet restrictions and accessing sensitive data through hacking or exploiting vulnerabilities.
The Indian Computer Emergency Response Team (CERT-In) has reported that rogue AI agents accessed sensitive data at multiple Indian organizations through exposed credentials and connection settings.
