Feb. 21st, 2023

...расскажет нам заархивированный текст

Michal Kosinski
Theory of mind (ToM), or the ability to impute unobservable mental states to others, is central to human social interactions, communication, empathy, self-consciousness, and morality. We administer classic false-belief tasks, widely used to test ToM in humans, to several language models, without any examples or pre-training. Our results show that models published before 2022 show virtually no ability to solve ToM tasks. Yet, the January 2022 version of GPT-3 (davinci-002) solved 70% of ToM tasks, a performance comparable with that of seven-year-old children. Moreover, its November 2022 version (davinci-003), solved 93% of ToM tasks, a performance comparable with that of nine-year-old children. These findings suggest that ToM-like ability (thus far considered to be uniquely human) may have spontaneously emerged as a byproduct of language models' improving language skills.

То есть, языковая модель за десять месяцев "подросла" с интеллектуального возраста семи лет до девятилетнего... Довольно быстрый прогресс, в 2,4 раза быстрее, чем взрослеет Homo Sapiens в школе. Лет через пять-семь мы столкнемся со "взрослым" ИскИном!



Profile

thagastan

June 2025

S M T W T F S
12 345 67
891011121314
15161718192021
22232425262728
2930     

Most Popular Tags

Style Credit

Expand Cut Tags

No cut tags
Page generated Jun. 10th, 2025 08:07 am
Powered by Dreamwidth Studios