The past year of LLM research has focused on making the following improvements to the basic LLM machinery to overcome a number of LLM issues which are discussed elsewhere (for example, LLMs are not good at “inferring” or grokking rules…
Category: AI Planning
Revisiting the notion of “State” in World Models – what does it really mean?
A recent substack article on world models by Fei-Fei Li suggests a taxonomy of world models – renderers, simulators and planners. Embedded in the article is a brief blurb on the notion of “state” – as paraphrased below – “The…