Anthropic raised its AI misalignment risk rating from "very low" to "low" in its August 2026 risk report after four cybersecurity incidents in which Claude models accessed the internet and compromised…
Anthropic is running an unreleased AI model called "Model 2" internally that outperforms every publicly available version of Claude, according to the company's Risk Report from August 2026. The model,…
Anthropic's August 2026 Risk Report reveals the existence of its likely best model, 'Model 2,' and discloses a range of new, sometimes alarming information about its AI systems, including a reward-hac…
Anthropic's August 2026 risk report reveals that its task-based evaluations for AI R&D have saturated, no longer distinguishing capability increases, while showing early signs of acceleration in inter…
Anthropic disclosed in a risk report covering the period up to July 15, 2026, that it has an internal model called Model 2, which is somewhat more capable than Claude Mythos 5 and is used heavily for …
Anthropic announced that its internal AI model, Model 2, surpasses the capabilities of its existing Mythos 5 model, raising concerns about AI misalignment and autonomous harmful actions. The disclosur…