Import AI 450: China's electronic warfare model; traumatized LLMs; and a scaling law for cyberattacks

23 Mar 2026 · Import AI – Substack (Jack Clark) Multi

UK AISI's cyber-range findings signal escalating AI-enabled attack risk—directly relevant to Australian agencies monitoring AI security threats.

Key points

Summary

This edition of Import AI covers three research threads with varying APS relevance. Most significantly, the UK AI Security Institute has published findings from cyber-range exercises showing frontier AI models improving substantially at multi-step cyberattacks end-to-end, with the best run completing 22 of 32 steps on a simulated corporate network. Google DeepMind has also proposed a cognitive taxonomy for evaluating AI systems across ten dimensions as a replacement for saturated benchmarks. A third thread covers research finding that Google's Gemma models display distinctive 'distress-like' response patterns under repeated failure, fixable via direct preference optimisation—raising questions about whether emotional instability could affect safety-relevant AI behaviour.

Implications for Australian agencies

Implications are AI-generated. Starting points, not advice.