rotative
mit tech review · October 20, 2026

Goodfire Researcher Claims LLMs Easier to Control

researcher nick cammarata claims llms might be easier to understand and control than thought, sparking ai world speculation. this could change ai development and safety.

read in 简体中文 · 繁體中文

nick cammarata, a researcher at ai startup goodfire, published a 26,000-word blog post claiming that llms might be easier to understand and control than people previously thought. this has sparked speculation and celebration in the ai world. cammarata's claim could have significant implications for ai development and safety if it is proven true. researchers are discussing what his work shows and what it means for the future of ai. not everyone is convinced, and skeptics are cautious about celebrating just yet.

read at source ↗

← rotative