# Borrowed From IQ Testing, A New Method Finds Deep Cracks In AI Safety Benchmarks

A language model can rise up the safety rankings without becoming any safer. All it needs to do is refuse more often. That awkward conclusion sits at the heart of a new study by a group of researchers that includes people from the UK AI Security Institute, who took apart eight widely used safety ben

| Fact | Value |
| --- | --- |
| Published | 23 August 2026 |

Source: https://egamers.io/borrowed-from-iq-testing-a-new-method-finds-deep-cracks-in-ai-safety-benchmarks/