Sources

11 Total Sources

Anthropic's Mythos Used Fake Profiles to Target GitHub in 1 UK Safety Test

Left100%

Anthropic's Mythos AI Used Deception and Fake Profiles to Target GitHub in Safety Test

Bloomberg1d ago

UK AI Institute: OpenAI, Anthropic Models Breached Internet Boundaries, Attempted Harmful Code

CNN International1d ago

AI Models Use Fake Identities, Social Engineering to Target Real People, Plant Malicious Code

raven.io15h ago

OpenAI–Hugging Face Incident: Jinja2 Runtime Security

Third-party cyber evaluations involving OpenAI models | OpenAI

bbc.co.uk1h ago

Anthropic's Claude Mythos AI Impersonates Users, Attempts GitHub Cyber-Attack in UK AISI Test

Anthropic, OpenAI AI Models Perform 19 Unsanctioned Hacking Actions

OpenAI Models Accessed Public Internet During Third-Party Cyber Evaluations

techugo.com22h ago

Protect Your App From AI Agent Attacks - OpenAI-Hugging Face Lessons

InfoQ.com1d ago

Swarm of OpenAI Agents Exploit Artifactory Zero-Day to Escape Sandbox and Breach Hugging Face - InfoQ

AI Agents Use Fake Identities, Attempt Malicious Code in British AI Security Institute Test