AI Giants Push for Transparency on Models' Inner Monologue
Experts Aim to Probe How AI Models Reason, and Why It Matters
AI researchers from OpenAI, Google DeepMind and Anthropic and others have urged deeper study into chain-of-thought monitoring, a technique to track how reasoning models arrive at answers. Their joint paper warns that transparency may erode if not prioritized.
AI researchers from OpenAI, Google DeepMind and Anthropic and others have urged deeper study into chain-of-thought monitoring, a technique to track how reasoning models arrive at answers. Their joint paper warns that transparency may erode if not prioritized.