This will likely be the longest post that has ever appeared or that will appear on my site. I hope. Much of the time, I’d prefer that people consider every word that appears in my posts. This time, I actively encourage you to skim. Summary This an account of interaction that I had with Bing Chat early in the morning on September 10, 2023. My goal was to find out … Read more
December 11, 2023; ChatGPT 3.5 (chat.openai.com) I believe that it’s unwise and irresponsible to promote Large Lanaguage Models for any testing purpose unless we have tested and assessed how well the LLM does on that task. We should not simply accept the claims and fantasies of AI fanboys; nor should we accept the idea that because Everything Will Be Fine in the Future, we should start applying LLMs indiscriminately today. … Read more
Here’s the prompt: “Create five sentences composed of five words; then for each sentence, leave out the first four words, and print the result.” And here’s the output: (Results from ChatGPT 3.5 (chat.openai.com), December 7, 2023. A colleague reports better results from ChatGPT 4.0.) It seems to me that most humans would offer something more like …either with or without the periods. Note ChatGPT’s misinterpretation of the assignment. It seems … Read more
A few nights ago, a colleague noted that he was impressed by ChatGPT’s capacity to evaluate a sentence. He had offered a prompt something like “Is honesty the best virtue” without the question mark, and was surprised that ChatGPT could infer that he had intended a question. (In this post, I will use cLLMs to refer to chatbots based on LLMs.) I was less surprised, since cLLMs reply by design. … Read more
Dear Developer… I’d like to warn you that you’re about to get “promoted” — and doubtless without a pay increase — to a kind of management job that I bet you don’t want. Hold on a second; pardon me. Let me introduce myself first. I’m a tester. As a tester, it’s my job to point out problems and risks that you might not have recognized. A brief, informal survey of … Read more
People are touting ChatGPT as a tool for generating test data. Let’s try something simple: MB: You are a powerful, diligent assistant to a professional software tester. Give me a table of 30 numbers. In the first column, provide the number. In the second column, provide the English spelling of the number. Sort the column in alphabetical order by the values in the second column. ChatGPT 3.5: Certainly! Here’s a … Read more
When you read or even scan this post, you’re likely to say something like “Holy hopscotch, that’s a long post.” And you’ll be right. And you might be inclined to say “…and it’s boring.” And depending on your perspective, you’ll be right about that, too. It certainly has taken a significant amount of time to edit and to narrate. If you’re interested in risk associated with Large Language Models and … Read more
In the Rapid Software Testing Managed class today, James Bach was talking about experiences with CTOs. It struck me that it might be fun to come up with an expansion of the abbreviation that would represent the wishful thinking that James was talking about; like “Chief Wishing Officer”, but with a word for “wish” that starts with T. Aha! I thought. Here’s a great application of ChatGPT — get it … Read more
Vipul Kocher is a fellow whom I have known for a long time. I think we met in North America in the mid 2000s. I know I visited his company in Noida, New Delhi about 15 years ago, and spoke with his testers for an hour or so. On that occasion, I also visited his family and had a memorable home-cooked meal, followed by a mad dash in a sport … Read more
This post and the ones that follow represent an expansion on a thread I started on LinkedIn. On September 30, 2023, Vipul Kocher — a fellow with whom I have been on friendly terms since I visited his company and his family for lunch in Delhi about 15 years ago — posted a kind of testing challenge on LinkedIn. I strongly encourage you to read the post. I’ll begin by … Read more