Thursday, February 08, 2024

How the Theory of Mind Might Have Spontaneously Emerged in Large Language Models

It is only a question of time when artificial intelligence (whether build on computer hardware or from biological tissues/cells etc.) will exceed current human intelligence. No reason to worry or panic!

If humans really were intelligent, there would be e.g. little or no success for the Global Warming hoax and Climate Change religion! This propaganda and demagoguery would be easily dismissed as a bad joke and medieval superstition!

"... Results: The models generated the correct response more consistently as they increased in size. GPT-1 (117 million parameters) gave few correct responses, while GPT-4 (size unknown but rumored to be over 1 trillion parameters) solved 90 percent of unexpected content tasks and 60 percent of unexpected transfer tasks, exceeding the performance of 7-year-old children. ..."

From the abstract:
"We explore the intriguing possibility that theory of mind (ToM), or the uniquely human ability to impute unobservable mental states to others, might have spontaneously emerged in large language models (LLMs). We designed 40 false-belief tasks, considered a gold standard in testing ToM in humans, and administered them to several LLMs. Each task included a false-belief scenario, three closely matched true-belief controls, and the reversed versions of all four. Smaller and older models solved no tasks; GPT-3-davinci-003 (from November 2022) and ChatGPT-3.5-turbo (from March 2023) solved 20% of the tasks; ChatGPT-4 (from June 2023) solved 75% of the tasks, matching the performance of six-year-old children observed in past studies. These findings suggest the intriguing possibility that ToM, previously considered exclusive to humans, may have spontaneously emerged as a byproduct of LLMs' improving language skills."


No comments: