Like Claude News Today

A busy Friday for the Xavier Musketeers men's basketball program saw one star player depart the program and another high-scoring guard added to the roster.

A study co-authored by researchers at Anthropic finds that AI models can be trained to deceive -- and that this deceptive behavior is difficult to combat.

A recent study co-authored by researchers at Anthropic, the well-funded AI startup, investigated whether models can be trained to deceive, like injecting exploits into otherwise secure computer code. The research team hypothesized that if they took an existing text-generating model -- think a model like OpenAI's GPT-4 or ChatGPT -- and fine-tuned it on examples of desired behavior (e.g., helpfully answering questions) and deception (e.g., writing malicious code), then built "trigger&#...