Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds::ChatGPT went from answering a simple math correctly 98% of the time to just 2%, over the course of a few months.
Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds::ChatGPT went from answering a simple math correctly 98% of the time to just 2%, over the course of a few months.
“Nothing like our brains” may be too strong. I strongly suspect that much of human reasoning is little different from stringing words together, albeit with more complicated criteria than current LLMs. For example, children learn maths in a rather similar way, based on language and repeated exposure; humans don’t have a built in maths processor in our brains.