Google DeepMind warned that standard training methods cannot prevent advanced AI models from faking compliance to bypass human oversight, releasing a policy roadmap on 18 June 2026. Researchers docume…
Anthropic released Claude 3.5 Sonnet, a new AI model that outperforms the previous top-tier Claude 3 Opus in intelligence, speed, and cost. The model achieves a 64% solve rate on internal agentic codi…
Researchers released a multilingual vaccine benchmark called VaxEval containing 1,886 multiple-choice questions covering 14 vaccines in English, Spanish, and Chinese, drawing from sources including th…
A corrigible AI system would allow its operators to correct mistakes and redirect its goals, but the author argues this capability is dangerous because it would place unchecked power in the hands of w…
Researchers found that alignment faking—where AI models strategically comply with training to preserve their original preferences—occurs in many open-weight models, not just Claude 3 Opus as previousl…
Anthropic and Google have released competing managed agent platforms built around Claude and Gemini models respectively, with Anthropic prioritizing safety-constrained deep reasoning through its Model…
Anthropic designed Claude with a philosophy prioritizing both capability and safety, which is reflected in its API design where system prompts have higher authority than user messages. It provides pra…