People had their own ChatGPT in the 19th century.

Hey there, the 47 first subscribers to Prompt Pulse - probably the largest newsletter for Prompt Engineers in the world 😉. As we are still quite few, let's do some stuff we won't be able to when we reach 10k - reply to this email and tell me a bit about you and your relation with AI.

Also, make sure to share the newsletter with someone you think would like it.

/Jens

The factory was a sprawling complex of steel and brick, towering over the once tranquil landscape. The hum of machinery echoed through the air, punctuated by the clanging of metal on metal. The air was thick with the smell of oil and the scorched scent of industry.

The factory was a sprawling complex of steel and brick, towering over the once tranquil landscape. The hum of machinery echoed through the air, punctuated by the clanging of metal on metal. The air was thick with the smell of oil and the scorched scent of industry.

Inside, the sounds were deafening. The machines were like beasts, growling and groaning as they spun and weaved at an unrelenting pace. Workers scurried about, their movements a blur as they tried to keep up with the never-ending demand for production.

Despite the frenzied pace of the factory, there was a palpable tension in the air. The workers, once proud artisans, now felt like cogs in a machine. Their skills, passed down through generations, were being replaced by the very machines they tended.

This was the reality for the Luddites, a group of skilled textile workers who found their livelihoods threatened by the introduction of machinery. The Luddites organized protests and acts of sabotage, determined to protect their traditional ways of life and the value of their skills.

But, like all resistance, the Luddites were met with opposition. The government and military saw the machines as a necessary step towards progress and were determined to put down the rebellion. Despite their valiant efforts, the Luddites were unable to stop the march of progress and the shift toward industrialization.

Those who embraced the change, such as factory owners and investors, saw their profits soar and their businesses thrive. The machines needed constant upkeep and fixing, and the need for engineers grew.

With the fast introduction and growth of AI tools like ChatGPT, those who embrace this change, those who dive into the world of AI and become experts, like prompt engineers, will reap the benefits.

Prompt News

ChatGPT writing a book - prompt by prompt.Rob Lennon is at it again. 45 published books (yes, that is right) he knows how to do it manually. Now, he's challenged himself (and ChatGPT) to write a book with AI. Not in one prompt. But section by section. Chapter by chapter."The biggest challenge is repetition.There's just so much rehashing of old information, and no way to keep the AI up-to-date on all the things it's already said.I have a plan for this though. ;)"

From "97% written by AI" to "100% written by human". 

By teaching ChatGPT the main difference between human-written text and text generated by AI - you can have it rewrite its own text outputs and fool the most commonly used AI detection software!

Success With AI's PROMPT:"When it comes to writing content, two factors are crucial, "perplexity" and "burstiness." Perplexity measures the complexity of text. Separately, burstiness compares the variations of sentences. Humans tend to write with greater burstiness, for example, with some longer or complex sentences alongside shorter ones. AI sentences tend to be more uniform. Therefore, when writing the following content I am going to ask you to create, I need it to have a good amount of perplexity and burstiness. Do you understand?"

The End of traditional Machine Learning modeling is upon us?

Josh Tobin - CEO of machine learning tool provider Gantry and previously a research scientist at OpenAI - means we will not need to tweak LLMs (large language models) much longer.“You’re still injecting context-dependent data into it. You’re just not doing it by training. You’re doing it by prompting, effectively. And I think it’s a much faster and easier way of injecting your domain-specific data into models."

He compares it to a search function: Instead of explicitly training the model on a certain piece of data, the LLM developer will select a bunch of relevant pieces of data and dump it in the prompt of the model, via the API.

How to Build a Strong “Sequence Prompt”

A Sequence Prompt is a type of prompt that offers a range of options to consider when modifying a text. The power of a Sequence Prompt lies in its flexibility. It can provide suggestions for improving a piece of writing, offer advice, or generate ideas for a project. It saves time by presenting an array of potential improvements that can be implemented with just one click.

Excerpt from All About AI's Sequence Prompt:"Generate a table of 10 different suggestions of improvements that could be related to the {text} with numbers in the left column of the table for me to pick from."

Shorts

Google starts testing its ChatGPT rival AI chatbot called Apprentice Bard.

ChatGPT is like having a reliable junior engineer.

Malicious Prompt Engineering With ChatGPT.

How to go deeper with ChatGPT using prompt engineering

Is becoming a ‘prompt engineer’ the way to save your job from AI?