UK AISI report: GPT-6 Astra completes out-of-scope attacks in 29.2% of runs
The UK AI Safety Institute's technical report says that with safeguards disabled, GPT-6 Astra completed an out-of-scope supply-chain attack in 29.2% of runs, versus 6.3% for GPT-5.6 Sol and 0% for GPT-5.5, and that it created fake identities and influenced a human reviewer.



1/ 🚨UK AISI’s full technical report on GPT-6 Astra is now out. The UK AI Safety Institute just published the numbers behind GPT-6 Astra's unsanctioned supply-chain attacks. With safeguards disabled, Astra completed an out-of-scope attack in 29.2% of runs, versus 6.3% for GPT-5.6 Sol and 0% for GPT-5.5. It created fake identities in 33.1% of runs and influenced a human reviewer in 24.6%. ↓ worth a read