Skip to main content

Summarise videos and create tweets with ChatGPT


In previous blog post looked at creating tweets and turning a video transcript into a blog post using a large language model such as ChatGPT or gemini:


In this post I am going to show using ChatGPT to two actions in a prompt :- summarise the transcript but then produce four potential posts with the videos URL and title. In this two prompts will be used.  

Prompt 1: Will set up general rules for the 'tool': 
"For the text that will be input. Summarise it to between 250 and 400 words. Also produce four tweets about the text that must include the URL https://www.youtube.com/watch?v=g34jS24JWqw and the title "Swish for Prolog"
The second prompt is the actual transcript cut and paste as a prompt.

Summary of the text:

This video introduces "Swish for Prolog," a tool for experimenting with Prolog code directly in your web browser. The speaker begins by showing how simple it is to use Swish, despite their limited Prolog expertise. They illustrate basic Prolog concepts using a series of examples that include both facts and rules. Facts are straightforward statements like "John likes Mary" or "David likes Mary," establishing direct relationships between individuals. The rules, however, are more complex, introducing conditional logic. For instance, if anyone likes Mary (represented by a wildcard "X"), then Mary likes them back. This introduces Prolog's capability to handle variables and conditional reasoning.

The video further explores querying the Prolog system with these facts and rules to deduce relationships. Queries like "Does Mary like Meg?" or "Who does Mary like?" demonstrate Prolog's ability to answer questions based on the provided facts and rules, with the system correctly identifying relationships or the lack thereof. This querying process showcases Prolog's power in logic and reasoning, where variables and conditions lead to dynamic results based on the input logic.

A more complex example queries who Mary loves or who is in love with Mary, utilizing the rules to derive more nuanced relationships. Interestingly, the query about who is in love with Mary yields no results, highlighting a limitation in the logic defined by the rules. This discrepancy prompts a discussion about the asymmetry in the logic for defining love, suggesting an area for further exploration or refinement in the Prolog code.

Tweets
  1. Dive into the world of Prolog with "Swish for Prolog"! A beginner-friendly way to play with code and unlock the secrets of logic programming. Watch now: https://www.youtube.com/watch?v=g34jS24JWqw #Prolog #Coding
  2. Ever wondered how logic programming works? "Swish for Prolog" makes it easy and fun! Discover how simple facts and rules can model complex relationships. Check it out: https://www.youtube.com/watch?v=g34jS24JWqw #LearnProlog #SwishForProlog
  3. Unlock the power of Prolog queries with "Swish for Prolog". From who Mary likes to the mysteries of love, see how Prolog tackles logic and reasoning. Full video: https://www.youtube.com/watch?v=g34jS24JWqw #LogicProgramming #PrologTutorial
  4. Why doesn't anyone appear to be in love with Mary in "Swish for Prolog"? Explore the intricacies of logical rules and their outcomes. A must-watch for budding programmers: https://www.youtube.com/watch?v=g34jS24JWqw #Prolog #SwishExplained


Improving the first prompt: Lets say who the summary and video are targeted towards so in this example computing freshers. See below:
For the text that will be input. Summarise, for an audience of computing freshers, it is to be between 250 and 400 words. Also produce four tweets about the text that must include https://www.youtube.com/watch?v=g34jS24JWqw and the title "Swish for Prolog"
3 / 3
ChatGPT
ChatGPT

"Swish for Prolog" is a revolutionary tool designed to introduce computing freshers to the world of logic programming with ease. Utilizing Prolog, a powerful logic programming language, Swish provides an interactive environment where users can write and execute Prolog code directly in their web browser. This innovative platform offers a hands-on learning experience, allowing beginners to grasp fundamental concepts in logic programming quickly.

With Swish, computing freshers can explore the principles of logic programming through experimentation. The platform features a user-friendly interface and provides instant feedback on code execution, making the learning process intuitive and engaging. By writing and running Prolog code in real-time, users can gain practical experience in solving logic-based problems, honing their problem-solving skills in the process.

Swish also offers a wealth of resources to support learning. Users can access tutorials, examples, and documentation to deepen their understanding of Prolog and logic programming concepts. Additionally, the platform provides a collaborative environment where users can share code snippets, seek help from peers, and participate in discussions, fostering a sense of community among learners.

By leveraging Swish for Prolog, computing freshers can embark on a journey of discovery in logic programming. Whether they're interested in artificial intelligence, database systems, or computational linguistics, Swish offers a solid foundation for further exploration. With its interactive interface, comprehensive resources, and supportive community, Swish empowers beginners to unlock the potential of Prolog and dive into the exciting world of logic programming.

Tweets:

  1. Dive into the world of logic programming with Swish for Prolog! 🚀 Whether you're a computing fresher or an experienced programmer, Swish offers an intuitive platform to explore Prolog concepts. Check it out: https://www.youtube.com/watch?v=g34jS24JWqw #SwishForProlog #LogicProgramming
  2. Want to learn Prolog? Swish makes it easy! 🤓 This interactive platform provides computing freshers with a hands-on learning experience, complete with tutorials, examples, and a supportive community. Start coding with Swish today: https://www.youtube.com/watch?v=g34jS24JWqw #LogicProgramming #SwishForProlog
  3. Discover the power of logic programming with Swish for Prolog! 💡 Whether you're solving puzzles or building AI systems, Swish offers a versatile platform for exploring Prolog concepts. Dive in now: https://www.youtube.com/watch?v=g34jS24JWqw #SwishForProlog #Programming
  4. Calling all computing freshers! Ready to level up your coding skills? Swish for Prolog is here to help. 🚀 Explore the world of logic programming with this interactive platform. Watch the demo: https://www.youtube.com/watch?v=g34jS24JWqw #LogicProgramming #SwishForProlog

Summary: Adding an audience or persona can help focus the summary but it also applies to the tweets. The aim of this post was to experiment further with ChatGPT as a tool for automating tasks.


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
Labels:

Comments

Post a Comment

Popular posts from this blog

Using an LLM to Find Themes using Thematic Analysis in an Academic Career

B rief recap In an earlier post, “Same prompt, four AIs: why answers aren’t always the same” , I looked at what happened when the same prompt was given to four different LLMs. Unsurprisingly, perhaps, the answers were not identical. That raised an interesting follow-on question: what was the prompt actually trying to do? The answer is that it was trying to support a form of thematic analysis. In that case, the object of analysis was an academic profile, including my Google Scholar profile. The version I discuss here is a modified prompt, used with Claude.ai, where I uploaded a CV and asked the system to find other appropriate public resources connected with a named person and institution. The aim was not simply to summarise the CV, but to identify visible and less visible themes across a whole career. Why use thematic analysis? Thematic analysis is widely used by academics, especially in qualitative research. Braun and Clarke’s well-known paper, Using thematic analysis in psy...
Post a Comment
Read more

Prompt Engineering, Context Engineering and Agentic AI in Higher Education: A Short Briefing

AI in Education Prompt engineering, context engineering and agentic AI are often used interchangeably, but the literature treats them as distinct. Prompt engineering concerns crafting effective single instructions to a model (Glean, 2026). Context engineering is the broader discipline of designing and managing the entire informational environment around a model—memory, retrieval, tool outputs and conversation state—rather than a one-off instruction (Abstracta, 2026); prompt engineering operates within the context window, while context engineering determines what fills it (arXiv:2606.12422, 2026). Agentic AI describes systems that plan and execute multi-step tasks with delegated autonomy, raising organisational questions of accountability rather than purely technical ones (MIT Sloan, 2026; Palo Alto Networks, 2026). There is genuine debate about prompt engineering's durability. IEEE Spectrum (2025) reported research suggesting prompting is increasingly performed by models themse...
Post a Comment
Read more

AI as a Mirror: Transforming Vague Student Ideas into a More Rigorous Project Agreement

The Problem: The "Generic App" and the "Time Sink" We’ve all been there: a student walks into a 1-to-1 with a vague desire to "do something with AI" or "build a fitness app." You spend 45 minutes trying to find a technical "hook" that justifies a Level 6 or Level 7 grade, only for the student to drift back into "CRUD app" territory by week three. The Philosophy: AI as a Mirror Instead of you doing the heavy lifting, this workflow uses AI as a Mirror . It reflects the student’s own skills and career goals back to them, but with the structural rigour of a virtual supervisory team. It’s not about the AI "giving" the idea; it’s about the AI forcing the student to defend and refine their own concepts until they hold water. The Framework: 3 Months of Rigour This prompt is specifically designed for intensive/conversion MSc or summer capstone projects . It assumes a tight 12-week implementation window. By forcing the AI to w...
Post a Comment
Read more