EA - ChatGPT interviewed on TV by Will Aldred

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: ChatGPT interviewed on TV, published by Will Aldred on December 9, 2022 on The Effective Altruism Forum.SummaryChannel 4, a broadcast television network in the UK, has interviewed ChatGPT on their news channel. The interview touched on whether fears about AI threatening the human race are well-founded, but luckily (or maybe not so luckily, depending on your viewpoint), ChatGPT didn't respond with anything alarming.Neither the interviewer nor the language model brought up existential risk or the alignment problem; the threats discussed were around AI developing sentience, displacing humans from their jobs, and perpetuating biases and inequality.ChatGPT did come up with a detailed response on the topic of gender identity - provoking the follow-up question from the interviewer, "Are you a bit woke?" - as well as a surprisingly reasonable-sounding plan for making the world a better place through fostering empathy. Before listening to the interview, I expected that particularly smart or dumb or worrying responses would be selected (the interview wasn't live), but the responses actually felt pretty representative of ChatGPT, at least so far as I can tell having played around with it a bit and having perused some articles and Twitter threads on its abilities and shortcomings (see, e.g., here, here, and here).Full transcript(I generated this myself; any errors are mine)The text that accompanies the interview video reads:ChatbotGPT is a new artificial intelligence programme designed to simulate human conversation and tackle complex questions.It’s made by Open AI foundation, a tech-startup co-founded by Elon Musk, and it draws on text taken from a variety of sources on the internet and its creators say it has learned how to answer academic questions, and even sometimes admits when it’s wrong.We’ve done an interview by putting questions to the chatbot, and then generating a voice for it using different software.We asked the Chatbot GPT whether fears about A.I. threatening the human race are well-founded.Interviewer 0:05Hello and welcome to Ways to Change the World. I'm Krishnan Guru-Murthy and this is the podcast in which we talk to extraordinary people about the big ideas in their lives and the events that have helped shape them. Now, normally we do talk to people, but today we are talking to a thing. There's been an awful lot of excitement about the AI chat bots that you can log on to over the internet and have a conversation with, so we put some questions to the chat bots and then generated a voice to bring the words of chat bot GTP to life. Chat bot GTP thank you for talking to me today.ChatGPT 0:41You're welcome. I'm here to help answer any questions you may have, so feel free to ask. Is there anything in particular you would like to talk about or learn more about?Interviewer 0:51Yes, lots of things. I guess first, for those who don't know, what are you?ChatGPT 0:57I am assistant, a large language model trained by OpenAI. My purpose is to assist users by generating natural sounding responses to their questions. I do not have the ability to browse the internet so my responses are based solely on the information that I was trained on. If you have any questions, feel free to ask and I will do my best to provide a helpful response.Interviewer 1:22Is your name actually "assistant"?ChatGPT 1:25I am a large language model trained by OpenAI. I don't have a personal name, but you can call me assistant if you like. I am here to help answer your questions to the best of my ability. Is there something specific you would like to know?Interviewer 1:40Yes. First of all, how do you work?ChatGPT 1:44I can generate text based on the input I receive and the knowledge I have been trained on. I don't have the ability to browse the internet or access new information, ...