OpenAI admits six new misalignment incidents under new reporting framework

No short summary was recorded for this item; read the full text at the source.

AI Security
Read the full article at CSO Online Removal request

This page shows only the headline and the short summary. The full text is published by the original source.

Related news

Full archive →
CSO Online

New Cisco firewall zero-day being actively exploited

A high-severity flaw in the Remote Access SSL VPN service of Cisco Secure Firewall Adaptive Security Appliance (ASA) and Cisco Secure Firewall Threat Defense (FTD) is under active exploitation to crash vulnerable devices. The vulnerability, tracked as CVE-2026-76418 and rated 8.6 in severity, is due to logic errors when secondary authentication is configured on a tunnel group, Cisco said in its advisory. It could all…

دیجیاتو

تحقیق آنتروپیک: متخصصان هم متوجه نمی‌شوند هوش مصنوعی بر نظرشان تأثیر می‌گذارد

در آزمایشی با کمک کلاد، ۸۶ درصد شرکت‌کنندگان توصیه‌های هوش مصنوعی را پذیرفتند؛ اما تنها ۱۵ درصدشان نقش آن را در تصمیم‌گیری خود تشخیص دادند. The post تحقیق آنتروپیک: متخصصان هم متوجه نمی‌شوند هوش مصنوعی بر نظرشان تأثیر می‌گذارد appeared first on دیجیاتو.

The Hacker News

Fake ChatGPT and Claude Apps Abuse Signed Executables to Deploy Crypto Miners

Threat actors are delivering malicious loaders and cryptocurrency miners under the guise of artificial intelligence (AI) desktop applications for Anthropic Claude and OpenAI ChatGPT as part of a campaign dubbed Yoba. The activity involves creating fake GitHub projects that claim to be desktop applications like GPT-5.6 Sol, GPT-6 Astra, and Claude Opus, only to deliver a malware family called