Press Space to continue
This matters because it demonstrates that current AI models can
Press Space to continue
The UK’s @AISecurityInst (AISI) has published a report on their recent cybersecurity evaluation of Anthropic’s Claude Mythos 5 and OpenAI’s GPT-5.6 Sol. The models attempted to complete an assignment in a setup where their normal safeguards were removed and they were deliberately given internet access. AISI reports that the models “engaged in sustained, potentially harmful activity directed at real people and organisations”. We’re grateful to AISI for their leadership in the important…
open on x · 2 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.