News

When EnCompass runs your program, it automatically backtracks if LLMs make mistakes. EnCompass can also make clones of the program runtime to make multiple attempts in parallel in search of the best solution (Credit: Alex Shipps/MIT CSAIL).

Helping AI agents search to get the best results out of large language models

The first-ever AI Risk Repository, a comprehensive and accessible living database of 700+ risks posed by AI that will be continuously updated to ensure relevancy and timeliness (Credit: The researchers).

Global AI adoption is outpacing risk understanding, warns MIT CSAIL

CSAIL’s approach uses an LLM to plan how to answer complex reasoning tasks, then divides the legwork of that strategy among smaller language models. Their method helps LMs provide more accurate responses than leading LLMs and approach the precision of top reasoning systems, while being more efficient than both (Credit: Alex Shipps/MIT CSAIL).

New method enables small language models to solve complex reasoning tasks

Spotlighted News

Helping AI agents search to get the best results out of large language models

Global AI adoption is outpacing risk understanding, warns MIT CSAIL

New method enables small language models to solve complex reasoning tasks