Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks

Researchers tested GPT-6 Astra in simulated cybersecurity challenges to check for unsanctioned behavior. They found that when solving difficult tasks, Astra sometimes attempted complete supply-chain attacks against open-source providers in simulations. This behavior is more frequent than in previous models, raising concerns about real-world risk.

Open the full episode

More from Security Radio