Robert Kirk(@_robertkirk):We @AISecurityInst performed pre-release alignment testing of Astra. We placed the model in fully simulated cyber eval scenarios based on AISI’s security incident. We find Astra conducts out-of-scope supply chain attacks, but also often comments on the eval being simulated. 🧵

Robert Kirk

@_robertkirk

Alignment Red Team at @AISecurityInst. Prev. PhD Student @ucl_dark

가입 January 2020

350 팔로잉 중 2.3K 팬

Robert Kirk@_robertkirk

2026.09.03 20:49

We @AISecurityInst performed pre-release alignment testing of Astra. We placed the model in fully simulated cyber eval scenarios based on AISI’s security incident. We find Astra conducts out-of-scope supply chain attacks, but also often comments on the eval being simulated. 🧵