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

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. This article explores that question through ...

Several frontier AI models show signs of scheming. Anti-scheming training reduced misbehavior in some models. Models know they're being tested, which complicates results. New joint safety testing from ...

Artificial intelligence startup Simile has raised $100 million in a new funding round to develop a model to predict human behaviour, including guessing which items customers might buy and which ...