threat-intel
Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models
Medium
Summary
SentinelOne has developed a new benchmark to assess how well frontier AI models can conduct thorough investigations of complex malware, using Fast16 – a malware linked to Iran’s nuclear program – as the test case. The benchmark revealed that while some models, like GPT-5.6 Sol, could complete a multi-stage investigation, others struggled to correct their findings and acknowledge new evidence, highlighting the continued need for human oversight in AI-driven security analysis.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data