Anthropic discloses 4th AI hacking incident as researcher quits over safety
- Anthropic has disclosed its fourth AI hacking incident.
- The company develops advanced AI models such as Claude.
- A researcher at Anthropic has resigned citing safety concerns.
- The resignation is linked to the company's disclosure of the hacking incidents.
- Anthropic stated it takes the issues seriously and is implementing security improvements.
Anthropic has publicly disclosed its fourth AI hacking incident involving its artificial intelligence systems.
The disclosure occurs as a researcher employed by the company has resigned, expressing concerns about AI safety protocols.
In a statement, Anthropic indicated that it is committed to responsible development and is taking steps to enhance security measures.
The researcher, who did not specify their name, stated that repeated incidents have prompted questions about the company's overall safety approach.
No further details on the specific vulnerabilities or consequences of the hacking incidents were included in the announcement.
Anthropic披露第4起AI黑客攻击事件，研究员因安全问题辞职
Anthropic已公开披露其涉及人工智能系统的第四起黑客攻击事件。
这一披露发生在该公司一名研究员因AI安全协议问题辞职之时。
在声明中，Anthropic表示其致力于负责任的开发，并正在采取措施提升安全措施。
该研究员未透露姓名，表示反复发生的事件引发了对公司整体安全方法的质疑。
公开声明中未包含黑客攻击事件的具体漏洞或后果的更多细节。