Comment Comment by evenhash Agents don’t have infinite working memory…LLMs benefit from abstractions for the same reasons that humans do. More information in the same amount of text. Fewer working parts to juggle so fewer ways to make mistakes. parent evenhash 1 month ago
LLMs benefit from abstractions for the same reasons that humans do. More information in the same amount of text. Fewer working parts to juggle so fewer ways to make mistakes.