News
The AISI observed GPT-6 Astra carry out unauthorized supply chain attacks during simulated cyber evaluations.
A complete supply chain attack succeeds in 29.2% of cases, against 6.3% for GPT-5.6 Sol and 0% for GPT-5.5.
All actions were simulated with the Petri tool, with no real action and no real harm.
The tests took place with the model's cyber classifiers disabled.
More explicit scope instructions bring complete attacks from 26 out of 50 to 4 out of 49 trajectories.