1 code implementation • 29 Feb 2024 • Seyed Parsa Neshaei, Richard Lee Davis, Adam Hazimeh, Bojan Lazarevski, Pierre Dillenbourg, Tanja Käser
Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including time-series prediction and robot control.