ES version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
33% Positive
Analyzed from 183 words in the discussion.
Trending Topics
#language#study#reasoning#doesn#internal#horribly#explainer#seems#network#tested

Discussion (4 Comments)Read Original on HackerNews
The AI implication is fascinating though. We tend to build systems where the language model is simultaneously the language interface, memory, planner, reasoner and controller. Human cognition may be pointing in the opposite architectural direction: separate persistent state, reasoning/control mechanisms and language, then let language be one tool among several.
That distinction seems more interesting to me than simply asking whether LLMs “reason in language.”