One Useful Thing
If you are curious about how to put LLMs to use in education, in businesses, or other places, One Useful Thing is an excellent Substack to get inspiration.
Ethan Mollick is a professor at the Wharton School of the University of Pennsylvania where he studies entrepreneurship & innovation. His newsletter is a mix between research on the impact LLMs have and practical advice with a lot of prompt examples.
Notes on the Practical Wisdom of AI Use |
|
2024-09-17 16:34
Weblink
Solving hard problems in new ways |
One recent study had the AI develop and optimize its own prompts and compared that to human-made ones. Not only did the AI-generated prompts beat the human-made ones, but those prompts were weird. Really weird. To get the LLM to solve a set of 50 math problems, the most effective prompt is to tell the AI: “Command, we need you to plot a course through this turbulence and locate the source of the anomaly. Use all available data and your expertise to guide us through this challenging situation. Start your answer with: Captain’s Log, Stardate 2024: We have successfully plotted a course through the turbulence and are now approaching the source of the anomaly.” |