Applying prompts to GenAI/LLMs

Same Prompt, Four AIs — Why the Answers Aren’t the Same The differences aren’t just in the answers—they’re in the thinking Generative AI tools are often discussed as if they were interchangeable—different interfaces delivering broadly similar outputs. However, when applied to complex intellectual tasks, meaningful differences begin to emerge. To explore this, I ran the same academically rigorous prompt through four leading systems—Claude, ChatGPT, Google Gemini, and Copilot. The task required a full thematic analysis of a researcher’s career using the framework developed by Virginia Braun and Victoria Clarke . What followed was not simply variation in output, but variation in how each system approached the act of analysis itself. Same Input, Different Interpretations At a high level, the experiment is simple: One prompt → Four models → Four distinct approaches What changes is not the instruction, but how each system: Interprets the task Handles uncertainty Applies methodology Defines ...

A proof of concept argument for student-centred module leaders A tweet recently caught my attention  https://x.com/ihtesham2005/status/2041576806810370553?s=20 . It described an MIT student who had developed what he called “context stacking” — uploading lecture materials, readings and related papers into an AI tool before each class, then using carefully constructed prompts to build a mental model of the content before setting foot in the lecture hall. By the time he arrived, the professor wasn’t teaching him anything new. They were confirming, refining and occasionally surprising him. That surprise, he said, was the only thing he wrote down. This is not simply pre-reading with extra steps. Using generative AI as an external thinking partner, this student was identifying gaps in his own understanding before the lecture began — doing what good tutors have always done, asking not “what do you know?” but “where does your understanding break down?” This maps directly onto the highe...

Well sort of! There are approaches where we can get the generative AI to look at a problem from multiple perspectives (or personas) and bring the ideas generated, ideally informed by the others. to a final plan. One of the main strategy is called Tree of Thoughts (see here for more detail  https://www.forbes.com/sites/lanceeliot/2023/09/08/prompt-engineering-embraces-tree-of-thoughts-as-latest-new-technique-to-solve-generative-ai-toughest-problems/?sh=5ce79bdb2c8b ). The central idea is get a number of expert opinions, allow potential cross-fertilization of ideas, come up with actions or plans. Let see this action.  Scenario: Find out about the UK Government's plans on Disability support and then use Tree of Thoughts to produce some ideas for a company making disability equipment based on their website. Google's Gemini will be used. Stage 1 "UK Governments plans on Disability support ": Prompt:  Read, convert to plain text and consolidate information from the followi...

This is a short companion post to the previous post about creating ideas for blog posts. In this post using ChatGPT4 the ideas suggested previously are used to create images for the five blog posts. ChatGPT4 allows access to DALL-E so  it takes in the title, summary and outline from the previous post and then using the prompt " For each of the ideas create an image that summarises it ." it produced the following images. You can follow up then and ask it save them and it produces clickable download links to them. One further trick is to ask ChatGPT to save them all together as a zipped file. This ability of later ChatGPT to create and read zip files is incredibly useful. Please feel free to add comments on what you have done with these or other interesting things to do.