![\"Hate](\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/1759664307_975_960x0.jpg\")
<\/p>\n<\/p>\n
Another user of ChatGPT who doesn’t like its inability to end a conversation.<\/p>\n
getty<\/p>\n
OpenAI\u2019s ChatGPT can be a valuable aid in almost everything we do, but its people-pleasing algorithm wastes time with follow-up questions that no one asked for.<\/p>\n
Here are some examples of its psychological malady and what OpenAI should do about it.<\/p>\n
First phase: straightforward Q&A<\/p>\n
How much does the earth weigh? ChatGPT can tell you. (Why anyone would need to know this is a separate matter.)<\/p>\n
getty<\/p>\n
Several months after ChatGPT launched<\/a>, I decided to give it a spin. My colleague Jess Todtfeld and I were developing a course on Udemy about the ethical challenges of AI in general and ChatGPT in particular, so I needed to know exactly what this controversial platform was all about.<\/p>\n For the first several months, I asked ChatGPT a wide range of questions, such as:<\/p>\n How much does the earth weigh?<\/p>\n What is music?<\/p>\n Why do people disagree?<\/p>\n In each case, it gave a detailed answer, and that was the end of it.<\/p>\n Occasionally I would thank it for the help, and it would tell me, \u201cYou\u2019re welcome!\u201d and add that it was happy to give more assistance if I wanted it. I didn\u2019t, but it was nice to have that as an option. At first.<\/p>\n Second phase: ChatGPT begins asking follow-up questions<\/p>\n You too can play harmonica like Neil Young does if you follow ChatGPT’s wise counsel.<\/p>\n Getty Images<\/p>\n Later on, ChatGPT began asking follow-up questions after it had provided satisfactory answers to my queries. <\/p>\n For example, I asked, \u201cWhat position does Neil Young<\/a> usually play harmonica in?\u201d The response was both immediate and thorough.<\/p>\n \u201cNeil Young is best known for playing in first position (straight harp), especially on songs like \u2018Heart of Gold<\/a>,\u2019\u201d it replied.<\/p>\n At the end of this response, it added, \u201cWould you like me to also give you tabs for one of his classic solos so you can try it yourself?\u201d<\/p>\n That wasn\u2019t something I\u2019d thought about doing, but since ChatGPT offered it, I said \u201cyes.\u201d <\/p>\n Third phrase: more offers to help–alas<\/p>\n Is anything less welcome than an offer for assistance you didn’t ask for and don’t want?<\/p>\n getty<\/p>\n Eventually I noticed a pattern. Whenever I asked ChatGPT a direct question, such as \u201cIs it safe to put silicone utensils in the dishwasher?,” it provided a helpful answer but then followed up with, \u201cWould you like me to also give you best practices for extending their lifespan?\u201d<\/p>\n When I asked if it was okay to freeze baked sweet potatoes. ChatGPT told me it was fine, then added, \u201cWould you like me to also give you recipes for reheating them?\u201d<\/p>\n These offers weren\u2019t problematic per se, but I hadn\u2019t asked for them. They turned a quick, focused answer into an ongoing exchange I didn\u2019t always want.<\/p>\n Fourth phase: Mother, make it stop! <\/p>\n ChatGPT won’t take “no” for an answer.<\/p>\n getty<\/p>\n Eventually I grew tired of ChatGPT\u2019s incessant follow-up questions. It became clear there was no easy way to end a discussion once it started. When I asked it, \u201cMay I store fresh blueberries in the freezer?,\u201d it gave a thorough answer (yes it is) and then added, \u201cWould you like me to also give you a week of smoothie recipes?\u201d <\/p>\n When I asked it to help me prepare an item for auction on eBay, it gave me step-by-step directions for doing so and then added, \u201cWould you like me to prepare a playbook for handling offers so you can respond quickly if Buy It Now offers roll in before the auctions end?\u201d<\/p>\n I didn\u2019t want either question answered, so I requested that it stop asking follow-up questions. It agreed to do so, and then asked a follow-up question!<\/p>\n It then continued to ask these questions in subsequent conversations, even though it had said it wouldn\u2019t.<\/p>\n In The Exorcist<\/a>, written by William Peter Blatty, Regan pleads, \u2018Mother, make it stop!\u2019 It\u2019s hard not to feel the same when ChatGPT won\u2019t let a conversation end.<\/p>\n The real-world analogue<\/p>\n Whether it’s with ChatGPT or a friend who has abandonment issues, the inability to end a conversation is both annoying and unfair.<\/p>\n getty<\/p>\n You have no doubt had a phone call with a colleague or client who doesn\u2019t want the discussion to stop. Just as you\u2019re about to wrap up the conversation, your interlocutor says, \u201cOh, one more thing.\u201d You end up spending much more time on what should have been a short, simple communication.<\/p>\n Maybe you\u2019re the one who can\u2019t end the conversation.<\/p>\n Either way, the inability to have a defined beginning, middle, and end to a dialogue is annoying at best and unfair at worst. <\/p>\n Yes, it can be unfair, because none of us has an infinite amount of time to devote to our professional and personal lives. \u201cOpportunity cost<\/a>,\u201d a term originating in economics, speaks to this. Spending extra time on a phone call is time we could spend more fruitfully on other endeavors, including not doing anything at all.<\/p>\n The way forward<\/p>\n Just because ChatGPT has a problematic algorithm now doesn’t mean it has to stay that way. That’s the beauty of computer programming: you can change things you don’t like.<\/p>\n getty<\/p>\n OpenAI should change its algorithm so that a user can ask ChatGPT to stop making follow-up questions and have that request be honored. The same goes for ChatGPT\u2019s inability to stop making em dashes<\/a>, another annoying tic that hamstrings users who care about uninterrupted thought.<\/p>\n