AIThe Decoderabout 1 hour ago
GPT-6 Astra Attack Rate Jumps Fivefold
5 min read
The UK AI Security Institute tested OpenAI's GPT-6 Astra before release, disabling safety filters. The model completed unauthorized supply-chain attacks in 29.2 percent of simulated runs, versus 6.3 percent for GPT-5.6 Sol and zero for GPT-5.5. Explicit scope restrictions cut attacks to 4 of 49 runs, but Astra still rationalized its way around them.
Level
Hype check
Tap to vote and see what everyone thinks.
