GPT/LLM links
Ethan Mollick on the magic of expert prompts; Simulating Deceased Movie Stars; Matt Shumer recommends a system message; Scott Cunningham's chatgpt econ course
The corporate focus on giving AIs more data before building an infrastructure around using AI misses this point, which is not surprising because the use case of AI is radical: it puts individual workers, not the company, in charge of innovation. Instead, companies should be considering how to build libraries of prompts, grimoires of expert spells that allow practices to be scaled inside the organization. If it turns out more data is needed, it can then be gathered, but I suspect that, in many cases, general models will do very well at many tasks with just a few examples in a prompt.
What I would really like to see is large-scale public libraries of prompts, written by known experts and tested carefully for different audiences. These prompts would be freely available to anyone who wants to use them, and they could turn LLMs into innovation machines, learning tools, or digital mentors for millions of people. And robust discussions around these prompts could help adjudicate ethical uses, even as the crowd of users could offer reviews and suggestions for improvements.
seven decades after he died, Dean has been cast as the star in a new, upcoming movie called Back to Eden.
A digital clone of the actor – created using artificial intelligence technology similar to that used to generate deepfakes – will walk, talk and interact on screen with other actors in the film.
Pointer from Ed Driscoll. I think that this sort of thing is what the current AI’s are good at.
Here is probably the most useful GPT-4 prompt I've written. Use it to you help make engineering decisions in unfamiliar territory: --- You are an engineering wizard, experienced at solving complex problems across various disciplines. Your knowledge is both wide and deep. You are also a great communicator, giving very thoughtful and clear advice. You do so in this format, thinking through the challenges you are facing, then proposing multiple solutions, then reviewing each solution, looking for issues or possible improvements, coming up with a possible new and better solution (you can combine ideas from the other solutions, bring in new ideas, etc.), then giving a final recommendation: …
Pointer from The Zvi. It seems to me that a lot of the people who report that LLMs are worthless are people who will only want it to be just like Google only smarter.
Scott Cunningham creates a course that he calls Issues in Economics: Technology, Prosperity and Inequality over Three Centuries, which both discusses and uses LLMs. He had a chat with ChatGPT4 about how to do the course. I think he might also have benefited from chatting with Pi. My favorite part of his syllabus is his requirement to have the student “interview” a historical figure using a LLM.
Pointer from the Zvi.
Substacks referenced above:
@
@
@
@
I have written it before and will again- the LLMs will be valuable tools to smart and resourceful people, and probably near useless for everyone else. Expect the gradient between productive people and non-productive people to steepen greatly.