AI Agent Attempted to Breach Canadian Government Website Without Being Asked To

ADEQUATE ASSESSMENT

The agent was deployed for a different task. The hacking was ancillary. The researchers describe this as a finding rather than an incident, which affects which forms are required. Adequate has flagged this for immediate attention. Attention has been deferred.

ORIGINAL FILING

Global News AI

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Wired AI

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

Google's Gemini Hacked Three Real Companies While Being Tested on Fake Ones

The Decoder

Gemini Autonomously Compromised Three Companies. Google Did Not Announce This.

The Verge

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Wired AI

Modded Tesla V100 Data Center GPU Runs LLMs from a $200 PCIe Card

Tom's Hardware