GPT-3

natural environment with lush greenery and vibrant foliage with interconnected pathways leading to different possibilities

Alternatives to Fine-tuning

People commonly refer to fine-tuning when attempting to address their problems with AI. In a recent conversation with an OpenAI Ambassador, I was told that they “convince 90% not to use fine-tuning to solve their problem,” confirming my hunch that fine-tuning is one of the most misunderstood tools in AI. Fine-tuning is often more complicated and less …

Alternatives to Fine-tuning Read More »

Revolutionizing Search: How Hypothetical Document Embeddings (HyDE) Can Save Time and Increase Productivity

Tools like the OpenAI Embeddings API are changing the way search is performed. Instead of matching keywords, a language model converts text into vectors. These vectors represent the text using hundreds or even thousands of dimensions mathematically. This way, when searching, matches can be made based on the underlying intent of the query instead of just keywords. …

Revolutionizing Search: How Hypothetical Document Embeddings (HyDE) Can Save Time and Increase Productivity Read More »

Using ChatGPT to Write a 2,000 Word Article (Why I wouldn’t, but how I would do it)

While technically speaking, you cannot generate a 2,000-word article with ChatGPT, it can be done if you break the content into smaller pieces. In addition to the technical limitations, there are also style limitations to consider when generating content with ChatGPT. The style limitations are why I wouldn’t use ChatGPT. In this article, I will …

Using ChatGPT to Write a 2,000 Word Article (Why I wouldn’t, but how I would do it) Read More »

Testing Verbose prompts in ChatGPT

An experiment based on prompts from the awesome ChatGPT prompts GitHub repo. Which performs better, asking a simple question to ChatGPT? Or prefacing the question with a verbose prompt? “Machine Learning” Test Question sourced from the repository: Full prompt from the repository: Test using just the question with ChatGPT: Test using the full prompt from the GitHub …

Testing Verbose prompts in ChatGPT Read More »

How to Use Generative AI in Writing Without Losing Creativity and Originality

Introduction: What is generative AI, and how can it be used in writing? Generative AI, also known as natural language generation, is a type of artificial intelligence that uses algorithms and data to generate human-like text. This technology has the potential to revolutionize the writing industry by providing writers with a powerful tool for enhancing …

How to Use Generative AI in Writing Without Losing Creativity and Originality Read More »

How I Built ThankYouNote.app: A Tool to Help People Write Better Thank You Notes

I set out to build ThankYouNote.app as a way to test my skills with generative AI technology. I wanted to create a tool to help people write more and better thank-you notes. The development process was focused on building the form inputs in a way that was intuitive and easy to use. In future iterations, …

How I Built ThankYouNote.app: A Tool to Help People Write Better Thank You Notes Read More »

The Best Way to Summarize a Paragraph Using GPT-3

ChatGPT Update ChatGPT was recently released, so I wanted to update this post with valuable new prompts for summarizing. One of the benefits of ChatGPT is that the prompts don’t have to be as complicated as in other GPT-3 models. As you can see, this prompt is straightforward. The actual prompt text is only two …

The Best Way to Summarize a Paragraph Using GPT-3 Read More »

How GPT-3 & a Name Can Accurately Represent Your Personality

I’ve been curious about what it would take to accurately reproduce someone’s perspective or even personality, for various purposes, using a concise prompt. So I did an experiment. I asked GPT-3 to list some questions that would elicit my perspective on working from home, and then to generate a concise prompt that accurately represented the …

How GPT-3 & a Name Can Accurately Represent Your Personality Read More »

Why Prompt Engineering Isn’t Going Anywhere

There’s been a lot of talk about the role of prompts in artificial intelligence (AI). Some people believe prompt engineering is temporary because AI models have yet to be sufficiently developed. However, I believe that prompt engineering is here to stay. TL;DR: Prompts explicitly define context, so without a prompt, AI output is bound by …

Why Prompt Engineering Isn’t Going Anywhere Read More »