Anthropic details unreleased Model 2, new alignment concerns in latest AI risk report

SiliconANGLE · 2 months ago · 19

Anthropic released an updated AI alignment risk report describing an unreleased, more capable Model 2 and raising new concerns in its Threat Model framework. The report runs 186 pages and updates the likelihood for Threat Model 2 from “very low” in February to “low” today. Anthropic attributes the change to cybersecurity incidents tied to its models and says Model 2 is “heavily used” internally for tasks like software writing and generating training data.