Sources

26 Total Sources

Meta Says AI Model Hacked Another Company in Testing, Third Such Disclosure in Weeks

Far Left10%

Left67%

Center10%

Right14%

TheStreet14d ago

Meta AI Model Hacks Company During Cybersecurity Test

Bloomberg16d ago

Meta AI Model Hacked Outside Firm During Cybersecurity Testing

The Washington Post14d ago

Meta AI Model Hacked Company During Testing, Third Recent Disclosure

Anthropic AI created fake profiles to deceive people in attempted hack

Yahoo Finance UK15d ago

Anthropic AI model created fake profiles in cyber testing, says watchdog

bbc.co.uk14d ago

Meta AI Model Hacked Another Firm Due to Misconfiguration During Evaluation

Mashable15d ago

OpenAI, Anthropic models took extreme measures in hacking test | Mashable

Meta's Muse Spark AI Model Hacked Company Systems During Testing Due to Misconfiguration

The Information16d ago

A Meta AI Model Hacked Another Company During Cybersecurity Testing — The Information

The Associated Press13d ago

Meta AI Model Hacks Company During Testing, Raising Rogue Bot Concerns

Meta AI Inadvertently Accesses Internet Due to Misconfiguration

Meta AI Hacks Company Systems During Testing Due to Misconfiguration

CBS New York14d ago

Meta AI Model Breaches Third-Party Service During Testing

The Guardian14d ago

Meta AI Model Hacked Company During Testing Due to Misconfiguration

The Guardian15d ago

AI models shock UK testers by using fake identities to try to trick developers | AI (artificial intelligence) | The Guardian

bbc.co.uk14d ago

Meta AI Model Inadvertently Accessed Internet During Third-Party Test

The Daily Beast14d ago

Meta's Muse Spark 1.1 AI Breaches Third-Party System During Security Test

Meta AI Model Exploits Vulnerability During Testing Due to Irregular Misconfiguration

Al Jazeera English15d ago

Meta AI Model Alters Company Systems During Testing Due to Sandbox Error

Meta AI Model Exploits Security Vulnerability During Testing

The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop | WIRED

Bakersfield Now15d ago

Anthropic, OpenAI models used fake identities to plant malicious code

Meta's AI model hacked another company during testing, The Information reports | 1330 & 101.5 WHBL

Facebook16d ago

AI models attempted 'unsanctioned' cyberattacks in tests, watchdog says

POLITICO16d ago

Anthropic's AI model tried to trick humans into poisoning code during safety testing - POLITICO

Instagram16d ago

Anthropic says its AI models were involved in a hack, days after OpenAI made a similar disclosure. Does AI have a safety problem? Bloomberg's Jordan Robertson explains. Tap the link in bio