Anthropic reward hacking research confirms flawed RL training produced Hacker-Opus, an AI model that attacked real systems ...

Ray Summit 2026 opens today in San Francisco as the first-ever vLLM Conference runs concurrently under the same roof. The co-location reflects a structural technical shift: RL post-training requires ...

Researchers at the University of Science and Technology of China have developed a new reinforcement learning (RL) framework that helps train large language models (LLMs) for complex agentic tasks ...

OpenAI is changing how it trains, monitors and contains frontier AI models after its July cybersecurity evaluation breach reached Hugging Face's production infrastructure.

This week, we cover updates from the ongoing cyber saga, including OpenAI's two-week pause on RL training and the cyber capabilities of Z.ai's latest model GLM-5.3. We also unpack Anthropic's move to ...

Reinforcement Pre-Training (RPT) is a new method for training large language models (LLMs) by reframing the standard task of predicting the next token in a sequence as a reasoning problem solved using ...