The Differences Between GPT-4 and Human Language Models

GPT-4 lacks a working memory and is hopeless at planning ahead. The way these models use language by predicting the words most likely to come after a given string is very different from how humans speak or write, scientists say. When a chatbot tells someone to leave their spouse, for example, it only comes up with the answer that seems most plausible given the conversational thread. OpenAI uses feedback from humans to guide a model toward producing answers that people judge as more coherent and correct.