BREAKING
UN Report: AI Guardrails Failed in Terror Test
0
models tested
0
prompts
0%
ChatGPT refusals
How models responded to harmful prompts
Full refusal57
Uplift33
Hedged compliance15
'Research' framing doubled compliance
Normal ask17
'Research' ask42
Highest vs lowest CT-AI Safety Score
Claude OpusScore 98
Led the field
Closed-weight model
Qwen3 8BScore 46
De-guardrailed
Cannot be recalled
High refusal rate is not safety
AI NEWS BLITZ
A UN-backed study finds AI chatbots often failed to block dangerous bomb-making queries.