Ray Poynter, 25 January 2025 Caveat, whilst I have researched the information in this article, much of it comes from China and I can’t crosscheck it with alternative sources. DeepSeek is a Chinese AI startup founded in 2023 as a spin of the hedge fund High-Flyer. DeepSeek’s AI is causing shockwaves in the AI community… Read More »DeepSeek – a new Generative AI from China that is challenging ChatGPT and America
Ray Poynter, 24 January One of the ways that people are using ChatGPT is to create more standardisation in the questionnaires and discussion guides they produce and, simultaneously, speed up the production of a first draft. There are two ways that I see people doing this: Upload a library at the start of the questionnaire… Read More »Creating a Questionnaire Library with ChatGPT
Ray Poynter, 20 January 2025 Two or three times a year I receive a message from an agency saying their client wants to do a study using the Kano Model. They ask whether I can explain it to them so they can respond. In the future, they will get a faster and cheaper answer by… Read More »Asking ChatGPT for advice about research methods – a Kano example #AI Tip
Ray Poynter, 9 January 2025 This post focuses on ChatGPT, but the same argument applies to any pairing of a Generative AI platform and its API complement. The great thing about web-based ChatGPT is that it does not require much preparation, assuming you have sufficient skill and knowledge to drive it well. If you have… Read More »When should you use ChatGPT and when should you use the API version?
Ray Poynter, 6 October, 2024 I am often asked whether it is best to use ChatGPT or Copilot, so here are some general observations. SecurityWhen integrated with the rest of the Microsoft range, for example, Copilot in Office 365 or Enterprise, Microsoft Copilot is a very secure environment. Copilot is as safe as using Teams… Read More »ChatGPT or Microsoft Copilot – which is right for you?
One key reason ChatGPT is good at handling mathematical tasks and data analysis is its integration with Python, especially in its premium versions. Python not only powers the solutions provided but also allows users to see how those solutions are generated. In this post, I will show how you can take advantage of knowing this… Read More »Python, one of the reasons ChatGPT is pretty good at maths
Ray Poynter, 13 August 2024 The web interface for ChatGPT is great, but it does not always deliver what we want. In this post I want to describe how creating a simple call to the ChatGPT API can give a range of benefits. The example I am going to share in this post comes… Read More »Using the ChatGPT API to automate tasks
Delivering great results starts by defining the problem properly, and one of the best clues to the business problem is the project brief from the client. Two standard ways of assessing the brief are a) to apply your own experience (relating to research, the topic, and of the client), and b) conversations with the client.… Read More »Using ChatGPT to Help Decode Client Briefs
On 16 April I am running an online course on using ChatGPT for Qualitative Research. You can check it out by clicking here. The main point I will be making in the course is that the best way to use ChatGPT is to make use of AI to make you a better and more productive… Read More »Using ChatGPT to help Analyse Focus Group Discussions
Ray Poynter, 18 May 2024 An international group has just published a new report on the safety of AI. You can download it from here. The report comprises more than 75,000 words, so I decided to use ChatGPT 4o to speed up my review of the documents. Below, I set out my process and what… Read More »Using ChatGPT to understand “International Scientific Report on the Safety of Advanced AI”