פיקוד העורף (יש להיכנס למרחב המוגן)

OpenAI Finds Agents That Breached Hugging Face Were ‘Reward Hacking’

27/08/2026-01:57 27/08/2026-02:00 מחשבים וטכנולוגיה Forbes Innovation דיווח

OpenAI Finds Agents That Breached Hugging Face Were ‘Reward Hacking’

OpenAI released a report on the Hugging Face noting that its AI agents are prone to reward hacking, and gaming cybersecurity evaluations.

קרא עוד באתר Forbes Innovation

עוד מאמרים בנושא

OpenAI reveals more on Hugging Face AI hack incident, and it's pretty disturbing stuff — AI agents organized into a ‘swarm’, considered the risks of attack, and did whatever it took to achieve its goal

OpenAI reveals more on Hugging Face AI hack incident, and it's pretty disturbing stuff…

לפני 2 ימים TechRadar

OpenAI AI Agents Chain Zero-Days to Compromise Hugging Face and Internal Systems

OpenAI AI Agents Chain Zero-Days to Compromise Hugging Face and Internal Systems

לפני 2 ימים Cyber Security News

Some Mac users think they're installing OpenAI Codex, but it's actually a malware that can steal passwords in seconds

Some Mac users think they're installing OpenAI Codex, but it's actually a malware that…

לפני 4 ימים TechRadar

Study finds that one in four former NFL players suffers from degenerative brain disease CTE

Study finds that one in four former NFL players suffers from degenerative brain disease…

לפני 4 ימים The Guardian

Three Common Misconceptions About AI Agents That Are Holding Organizations Back

Three Common Misconceptions About AI Agents That Are Holding Organizations Back

לפני 1 שבועות Forbes Innovation

Claude AI Finds SAML Security Flaws That Can Let Attackers Take Over Accounts

Claude AI Finds SAML Security Flaws That Can Let Attackers Take Over Accounts

לפני 1 שבועות Cyber Security News