![]() Q: Will supercomputers ever be smarter than people? Please enjoy this piece – and don’t miss the final words of advice from ChatGPT at the end of this interview followed by Eliza’s responses to the same questions (a bit disappointing, and hardly an accurate portrayal of the enthusiasm Eliza earned in her day).ĪI questions – can we trust ChatGPT and HAL 9000s? Another case for teaching and encouraging ethics.Īs you’ll see, ChatGPT appears to be designed to be objective, polite, and consistently resist “bait.” Will chatbots be useful resources, or troubling technologies? The reality, like it or not, is that technology can always be both. I can easily say the majority of people would not be as well versed as ChatGPT proves to be. Eliza was always terse with her replies and open to hearing back from the interviewer.ĬhatGPT answers all have some degree of merit, with occasional flaws blended in pus a few blunders. It would be fascinating to see what an expert thinks in 50 more years it is easy to see that we’ve seen some degree of progress since Eliza.ĬhatGPT is wordy and precise, in a way an engineer or scientist can love. Her comments follow my interview with ChatGPT.Īll the questions and answers are completely unedited, and despite adding a few notes I must emphasize that I am providing no endorsement on their accuracy. I also hunted down the original chatbot from over 50 years ago, Eliza, and offered her the opportunity to answer the same questions. Just like we all “Googled” ourselves in the early days of Google (and many still do), I could not resist asking questions to see if ChatGPT knew about me. I poke a bit with questions like “What is better: a fresh apple pie, HPCwire, or Qualcomm?” and “Was HAL 9000 trustworthy?” Along the way, I learn that ChatGPT is quite articulate about Fortran and denormalized numbers. ![]() I hope you find the interviews amusing and stimulating. I share the output, in no small part to document what I saw so it is available for comparisons 50+ years from now. I could not resist so I took a few minutes away from my time as an Intel oneAPI evangelist and did an interview with the most talked about chatbot of our day: ChatGPT (using their free plan). Guest contributor James Reinders “interviews” ChatGPT and Eliza on on topics that span trusting AI (including HAL 9000s), HPC, heterogeneous computing, Fortran, Python, and predicting the future.Ĭonversing with computers is inevitable, and our fascination with it and the famous Turing test are nearly infinite and span people from all walks of life. Since 1987 - Covering the Fastest Computers in the World and the People Who Run Them ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |