Anthropic (@AnthropicAI): Over the last few months, we’ve made significant progress in reducing the effectiveness of distillation attacks against Claude. In this post, we explain how:

Anthropic research shows small AI models may soon self-replicate on consumer IoT devices, potentially creating unstoppable malware that adapts across different hardware.

Harvard study finds AI coding agents increase code output by 30% but create review bottlenecks, resulting in no net gain in software production or employment reduction.

Researchers developed Prompteina, the first all-atom protein structure generation model that accepts natural language descriptions as input.

Frontier AI companies' current alignment plans center on rushing towards RSI with current models, which many believe will have catastrophic consequences.

Researcher shares empirical AI safety lessons from MATS and Redwood Research apprenticeships, focusing on misalignment auditing and sabotage capabilities.