OpenAI's o1 models are dramatically better at reasoning than previous LLMs, but they struggle with spatial reasoning and are far from human-level intelligence (Timothy B Lee/Understanding AI)

https://ift.tt/2a3urA5

Timothy B Lee / Understanding AI:
OpenAI's o1 models are dramatically better at reasoning than previous LLMs, but they struggle with spatial reasoning and are far from human-level intelligence  —  It's not easy to stump OpenAI's new o1 models. … You might remember around Thanksgiving last year when news broke about Q* …

from Techmeme https://ift.tt/a1f3Uje