June 2024: The latest general-purpose LLMs could not count the r's in strawberry.
Large language models are rapidly improving in their reasoning and problem-solving capabilities. While current models struggle with simple tasks like counting letters, projections suggest they will achieve significant milestones in complex domains like mathematics and theoretical geometry within the next two years. This rapid advancement indicates a trajectory towards highly sophisticated AI problem-solving. AI
IMPACT Projects rapid LLM progress in complex reasoning, potentially enabling breakthroughs in scientific and mathematical fields.