Why a Former AlphaGo Researcher Says Today’s LLMs Still Don’t Reason
Former AlphaGo researcher Thore Graepel argues that LLMs need auditable belief states and search, not simply longer chains of thought.
LLM Research
Latest News and Analysis in LLM Research
LLM Research
Study finds large language models can form hiring stereotypes faster than people
A new study reported by MIT Technology Review finds LLMs can form hiring stereotypes faster than humans, raising risks for AI screening tools.
Researchers Publish Breakthrough Internal Steering Technique for LLMs in Science Journal
UC San Diego and MIT researchers have published a landmark study in Science demonstrating a scalable method to steer and monitor AI models by directly manipulating internal concept representations, exposing both safety vulnerabilities and capability improvements.
Ads