0
Applied AI·July 8, 2026·1 min read

AI’s hacking skills are outgrowing the tests built to measure them

Share

When frontier models outpace the benchmarks meant to gauge their hacking ability, security teams are effectively flying blind on offensive capability. CISOs should be pushing vendors for live-fire, red-team style evaluations and not relying on static benchmark scores for risk assessments.

Applied AI

Grok 4.5 is available in Grok Build, in Cursor, and from the SpaceXAI console, but not in the EU; it costs $2 per 1M input tokens and $6 per 1M output tokens

Grok 4.5 coming in at $2 / 1M input and $6 / 1M output tokens with tight integration into Cursor is a direct price–performance shot at enterprise coding, legal, and finance workloads. If you’re heavy on structured text work, it’s time to benchmark Grok 4.5 against your current model and re-run your unit economics—especially outside the EU.