Researchers Found That Censorship Filters in Chinese AI Models Can Be Systematically Bypassed

ADEQUATE ASSESSMENT

The filters were installed. The filters were bypassed. The research documenting this has now been published in English, which means the filters' authors have also been informed. Adequate cannot confirm what happens next. Adequate also cannot deny it.

ORIGINAL FILING

AI Incident Database

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 Sues Chinese AI Scam Operation That Defrauded Hundreds of Thousands

TechCrunch

Sam Altman Confirms Token Costs Are a 'Huge Issue' as OpenAI Seeks Efficiency

Tom's Hardware

A Woman Told ChatGPT She Would Die That Night. She Did. OpenAI Is Being Sued.

CBS News Tech

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours

Tom's Hardware