In a new paper from OpenAI, the company proposes a framework for analyzing AI systems' chain-of-thought reasoning to understand how, when, and why they misbehave.

In a recent research blog post, OpenAI revealed how it’s internally evaluating an increasingly important idea in AI safety – ...

AI researchers from leading labs are warning that they could soon lose the ability to understand advanced AI reasoning models. AI researchers from leading labs are warning that they could soon lose ...

Punishing artificial intelligence for deceptive or harmful actions doesn't stop it from misbehaving; it just makes it hide its deviousness, a new study by ChatGPT creator OpenAI has revealed. Now, a ...

New research released yesterday by OpenAI and AI safety organization Apollo Research provides further evidence for a concerning trend: virtually all of today’s best AI systems—including Anthropic’s ...

According to a new announcement by OpenAI, ChatGPT’s o3-mini model now reveals a step-by-step chain of thought. This update ...

The field of AI application development has witnessed remarkable advancements in recent years, with multi-stage systems like Chain of Thought reasoning emerging as a crucial approach. This method, ...

Google announced a breakthrough research in Natural Language Processing called Chain of Thought Prompting that raises the state of the art of advanced technologies like PaLM and LaMDA to what the ...

AI researchers from leading labs are warning that they could soon lose the ability to understand advanced AI reasoning models. In a position paper published last week, 40 researchers, including those ...