Using ChatGPT to Help Decode Client Briefs
In this post, I will illustrate how to use ChatGPT to review a brief to probe for insights into the client’s research and business questions and provide clues as to what the client is likely looking for.
Why are Apple and Facebook Threatening to put Europe in the AI Naughty Corner?
Meta, the company that owns Facebook, has announced that it will not release its advanced AI model (an update to Llama) in the EU. They say this is because they fear European regulations. This news comes hard on the heels of Apple’s announcement that its generative AI tools may not be available in the EU. Here are some thoughts on the why?
Speaking Nicely to Generative AI Seems to Help Get Better Answers
In a paper published in April this year, researchers showed how speaking more collaboratively to LLMs seems to generate better responses. The paper describes how Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen conducted a series of experiments to explore how different strategies for prompts delivered different answers.
Refining and Regenerating Prompts – a ChatGPT tip from Ray Poynter
In this post, I will highlight two approaches to getting to a better answer from ChatGPT. The first is Refining and the second is Regenerating.
Converting images to text – ChatGPT Tips #1
In this tip I show how ChatGPT can convert the text in an image into text you an work with.
Using ChatGPT to understand “International Scientific Report on the Safety of Advanced AI”
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 I found out about the report.
Is weighting a form of synthetic data?
One of the surprises about the sudden and widespread interest in Synthetic Data is that it has forced us to revisit things we have been doing for decades. This revisiting of old practices is useful for framing where we think Synthetic Data should go and how it should be evaluated and regulated. In this post I explore why weighting is a form of synthetic data and what that means for researchers.
Synthetic Data –an Overview, a Taxonomy & some FAQs
AI is a hot topic, and in the insight and research ecosystem, the hottest topic is Synthetic Data. In this post, I look at what Synthetic Data means, why it is such a hot topic, some of the key issues, and share some thoughts about Synthetic Data and its use.
Using ChatGPT to help Analyse Focus Group Discussions
In this post, I want to highlight one way that ChatGPT can help you be more efficient. In this example, I have taken a Focus Group Transcript from a published study and used ChatGPT to help speed up my analysis.
Using memes to communicate the story in the data
Meme’s are a powerful medium of communication, the pass from person to person because they catch the attention, are memorable, and are easy to share. In this post Ray Poynter shows how to use them to help communicate the story in the data.