The article notes that selecting the right training style starts with identifying the type of behavior that needs improvement ...

A set of recent research papers proposes that freezing or selectively tuning a small fraction of neurons inside large language models can, in reported benchmark evaluations, reduce unsafe outputs ...

Anthropic is testing a new AI model that has exhibited an unusual behavior during safety evaluations: it told testers it ...

New research suggests that modern AI systems, especially large language models, cannot be understood in isolation but must be ...

The National Academy of Sciences is a private, nonprofit, self-perpetuating society of distinguished scholars engaged in scientific and engineering research, dedicated to the furtherance of science ...

Google Research has proposed a training method that teaches large language models to approximate Bayesian reasoning by ...

Two summer schools focused on skills for cognitive modeling and mathematical psychology will each receive $20,000 grants ...

Research shows that persona prompting "reliably" damages accuracy for some types of tasks but works well in other categories.

KA, HAB, on why treating feline behavioral conditions demands the same diagnostic rigor as any other medical diagnosis—and ...

Personality tests are widely used in workplaces to shape recruitment, leadership training and team building. But what if ...

Introduced early, these discussions can shape both behavior and health outcomes. Clients who understand normal feline ...