Skip to main content

Couple of interesting things week beginning 19th August 2024


A short post on two interesting, well to me anyway, sources I came across this week.

The first,  How to (majorly) boost your communications and content with ChatGPT (fasttrackimpact.com) the full article can be read via the link. Using Gemini to summarise it, the italicised text below was produced:

ChatGPT can significantly enhance your communication strategies and content creation. It can quickly draft content, brainstorm topics, write social media copies, summarize research, and create educational materials.

Key benefits of using ChatGPT:

  • Efficiency: Speeds up tasks like creating slide decks and communication strategies.
  • Creativity: Generates creative and coherent text for storytelling and audience engagement.
  • Versatility: Reshapes existing content for different purposes.

How to use ChatGPT effectively:

  • Clear instructions: Provide specific and detailed instructions.
  • Iterate: If the response isn't satisfactory, refine your instructions.
  • Prompt patterns: Use specific prompts like asking ChatGPT to act as a persona or asking leading questions.

Example: Creating an X thread from a research article:

  1. Divide the article: Break the article into smaller sections due to ChatGPT's character limit.
  2. Summarize: Ask ChatGPT to summarize each section.
  3. Create thread: Prompt ChatGPT to create an X thread based on the summaries.
  4. Refine: Add commentary, include visuals, and edit the concluding tweet.

Human oversight:

  • Verify responses: Ensure the content is accurate and appropriate.
  • Disclosure: Clearly state if ChatGPT was used in content creation.
  • Avoid plagiarism: Be mindful of copyright infringement.

Conclusion: ChatGPT is a valuable tool for enhancing communication and content creation. By following these guidelines and using it effectively, you can save time, improve your work, and reach a wider audience.



The second good bit of news is Lance Eliot, whose articles from Forbes Magazine which have been highlighted in this blog, has two books out:

"Essential Prompt Engineering for Generative AI" available at https://amzn.to/3MgxXde provides a guide to many of the common Prompt Engineering Strategies such as Chain of Thought (CoT) and Imperfect Prompting, along with many others. The language used is accessible and does not require specialist knowledge. 

There is a second book "Advances in Prompt Engineering for Generative AI" available at https://amzn.to/3YYAEro which not surprising extends the range of prompts and it does include two of my favourite ones Chain of Density (CoD) and Tree-of-Thoughts (ToT) prompting. 

I only brought these two books this week so when I have had the chance to work with them, I will share more.

-Tree-of-Thought Prompting is discussed in an earlier post: https://llmapplied.blogspot.com/2024/05/taking-to-yourselves-with-chatgpt-and.html

 - Chain of Density (CoD) of density is discussed in a couple of earlier posts:


All opinions in this blog are the Author's and should not in any way be seen as reflecting the views of any organisation the Author has any association with. Twitter @scottturneruon

Comments

Popular posts from this blog

GenAI Productivity: Ideas to project proposal 1

One of the ways I use Generative AI with students is to take basic ideas for projects, usually a title, and get these tools to greater ideas and start of a project proposal. This is with all the usual caveats  Check the references (if any); It is going to be basic, so extend it. In this example I am going to use Co-pilot but the ChatGPT, etc can be used, employing a few basic prompt engineering basics: personas (who is the target audience?) and Templates (how do I want it to look?) to start this process. Example:  Project ideas for MSc Data Intelligence students (persona)  on a particular topic. The reply will include subheadings and relevant (hopefully) content for  TITLE, INTRODUCTION, PROBLEM STATEMENT. The prompt: " Taking the topic "Leveraging open-source tools to measure and present academics publications automatically from public domain data.". Give five innovative projects for a Master's level student dissertation in Data Intelligence. Each project example wi...

GenAI Productivity: Ideas to project proposal ideas from Google Scholar

Generated as well by Google Gemini In previous blog posts, I have looked at generating project ideas for project ideas. These can be used with many different GenAI platforms . As an idea/challenge, I want to come up with a way for students to generate ideas for projects based on knowing who they would like to work with and that person's Google Scholar profile. Here is the catch: often, it can be difficult to access Google Scholar to do this. One solution  is to use Google Gemini, a Google product, to access another Google product. Going to apply this to my own profile - ego rides again . It went and did much when I click on it and deep research, it did a full research report. Prompt used :  " Using this as a starting point https://scholar.google.com/citations?user=ghQedZAAAAAJ&hl=en from the research here provide 10 project ideas suitable for a final year Computer Science student project with this supervisor. For each provide title, 100 word summary, possible outcome s...

GenAI Productivity: Ideas to project proposal 3

Produced using Google Gemini In two previous posts I looked at using Generative AI to start producing  project ideas and refining one to be the start of the proposal, Previous blog posts GenAI Productivity: Ideas to project proposal 1 GenAI Productivity: Ideas to project proposal 2 This post is really a slightly different variation on those. Playing with adding a few things in. The example can be repurposed for non-computing student but the example came from a discussion with a BSc Software Engineering student, thinking about project ideas Example starting prompt in ChatGPT4o " P roduce 5 project ideas suitable for a BSc Software Engineering students for the following topic: " Ambient Assisted Living " The project must suit someone with a strong interest in programming.  For each idea produce a 100 word description; justification in 200 words why this is a worthwhile project; a set of goals; sources of potential data; physical resources neede d " It does produce 5 p...