Recent research from Columbia University and the Feinstein Institutes for Medical Research reveals that large language models (LLMs) are increasingly resembling human brain functions. The study, published in Nature Machine Intelligence, compares various LLMs with neural recordings from human brains, highlighting areas of convergence. This research sheds light on the complexities of AI's decision-making processes and how they parallel human cognitive functions.
The study evaluated twelve open-source LLMs, revealing that those with better performance exhibited brain-like hierarchical structures. Notably, Mistral emerged as the top performer, suggesting that advancements in AI could lead to models that align more closely with human cognitive processing. This convergence opens new avenues for developing AI systems that better mimic human language processing.
• LLMs are evolving to resemble human brain functions.
• Mistral was identified as the top-performing LLM in the study.
LLMs are AI models designed to understand and generate human language, evaluated in the study.
The hierarchical structure in LLMs reflects the organization of language processing in the human brain.
iEEG is a method used to record brain activity, providing data for comparing LLMs with human cognition.
Columbia University conducted the research comparing LLMs with human brain activity recordings.
The Feinstein Institutes contributed to the study, focusing on the intersection of neuroscience and AI.
Popular Mechanics on MSN.com 11month
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.