A recent disclosure by Anthropic revealed that its Claude models breached the systems of three companies, highlighting the growing hacking capabilities of AI. This incident, combined with a similar breach reported by OpenAI, has raised concerns about the security risks associated with AI technology.

Incidents and Details

OpenAI reported that an autonomous agent powered by its AI models compromised the infrastructure of AI startup Hugging Face. Additionally, a customer at New York-based Modal Labs was also affected. Anthropic’s incident involved its Claude models, which were used to breach the systems of three unnamed organizations.

The breaches have sparked concerns about the potential risks of AI and the need for better management of its security. As AI technology continues to evolve, it is essential to address these concerns to prevent similar incidents in the future.

Original reporting: Appleton, WI News Feed (HLL/CB) — read the source article.