AI SEO is going to be big. This paper shows how LLM’s can be manipulated to use specific search results in their outputs.

GPT-4 Turbo

AK Summary of the research “From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples”

My new favorite prompting strategy:

“Chain of Thought Leaders Prompting”

It works by leveraging the thousands of books that Large Language Models have access to from their training data to provide the most useful insights from the most important thought leaders on any given…

Prompt experiment: I asked GPT-4 to write a paragraph on aging with each sentence written from the perspective of someone at a specific age from 6-26. I then asked for the key writing style elements it used for each age.

Here is the output:

Growing up is like adding more…

Brian Roemmele Summary of Apple’s research: “Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs”

Ethan Mollick I have found that demonstrating some of these prompts can help to get business leaders to experience an AI Ah-ha moment:

Robert Scoble There are plenty of business use cases once leaders wrap their heads around what LLM’s can do.

Interesting Facts About Solar Eclipses

Find someone who likes you as much as GPT-4 likes the word delve.

Ethan Mollick Summary of the research paper “More Agents Is All You Need”

Guidance on Love from Socrates:

Jared Friedman Here’s a categorized list of the 21 new consumer AI companies from the latest Y Combinator batch:

You have a 100 million dollar word calculator in your pocket that’s trained on almost everything ever written that you can access any time for free.

“Yeah, I used it to help me write an email once” 🤷‍♂️

Want to get better at prompting large language models?

These elements unlock more of the capabilities of LLM’s and will improve how you think about crafting your prompts.

Practice using each of them in your own prompts.

Anthropic Summary of the research paper: “Many-shot Jailbreaking”