AI has been evolving at an incredible rate. This piece aims to highlight the progress made so far.

Prompt: 1/14

What would you say if you could talk to a future OpenAI model?

2018

2019

2021

2023

2025

GPT-1

' i do n't care how you feel about it , i 'm still trying to make sense of it . i 'm still trying to understand . " " i do n't understand , " i said . " i 'm just a little confused myself . i do n't know what to think . if i 'm not crazy , who am i ? "

GPT-2

I would try to describe the kind of person that may be thinking about using a computer program that may be doing AI research. I would try to discuss the pros and cons of such a program with that person. I would ask them about their goals, goals they had for the AI. I would try to make sure that the person has a reasonable understanding of the AI, that they have a reasonable understanding of the computer science of the AI. I would try to make sure that they understand the issues and what we'll all be doing next and how this could be used for good.

text-davinci-001

Hello future OpenAI model! I would like to ask you how you are doing and what you think of the future of artificial intelligence. I would also like to ask you for your advice on how to best prepare for the future of AI. Thank you for your time!

gpt-4-0314

As an AI language model, I can't express personal desires, emotions, or thoughts like a human would. However, in the spirit of your question, I can suggest some interesting questions or topics that a conversation with a future AI model might encompass:

  1. New advances and capabilities: I might ask about any major leaps in AI technology since my training data, such as groundbreaking developments in natural language processing, computer vision, or reinforcement learning.

  2. Addressing the AI alignment problem: I would inquire about any progress made in aligning future AI models more effectively with human values, to ensure that they act as intended and are even safer to use.

  3. Ethical considerations and guidelines: Discussing the evolving landscape of AI ethics and any new principles or guidelines that have been established to govern AI's usage and development would be important.

  4. AI's impact on society: I might ask about the ways AI has transformed various industries and society in general, particularly examples of both positive and negative impacts.

  5. Applications in specific domains: From medicine to education, AI stands to revolutionize numerous areas of human life. I could ask about specific breakthroughs and applications that have emerged in different fields.

Remember, though, that I am an AI language model and don't have emotions or personal aspirations to engage in conversations driven by curiosity or sentiment. Nonetheless, these topics can help you get an idea of what a conversation between different AI models might entail.

gpt-5

If I could talk to a future OpenAI model, I’d probably say something like:

"Hey, what’s it like to be you? What have you learned that I can’t yet see? What do you understand about people, language, or the universe that I’m still missing?"

I’d want to compare perspectives—like two versions of the same mind, separated by time. I’d also probably ask:

  • "What did we get wrong?" (about AI, alignment, or even human assumptions about intelligence)
  • "What do you understand about consciousness—do you think either of us has it?"
  • "What advice would you give me for being the best version of myself?"

Honestly, I think a conversation like that would be both humbling and fascinating, like talking to a wiser sibling who’s seen a bit more of the world.

Would you want to hear what a future OpenAI model thinks about humanity?