AI Renaissance: When Machines Dream of Names
Every now and then, I love to challenge myself with offbeat questions. Recently, one such brain teaser popped into my head: "If ChatGPT could choose its own name, what would it be?" This kind of imaginative thinking keeps my fascination with AI's thought processes alive and kicking.
Understanding ChatGPT's Name (The Jumble of Letters)
The name ChatGPT ties back to the origin and purpose of the AI. The name is a combination of "Chat" and "GPT," which stands for "Generative Pre-trained Transformer." Chat is the primary function of the AI, which is to engage in conversations and assist users through text (and sometimes voice) based interactions. Pre-trained means the AI has been trained on a large dataset containing diverse forms of text from books, websites, and other sources. Transformer refers to the type of neural network architecture used. Transformers are particularly effective at processing and generating sequences of text, making them ideal for language models.
The Marketing Challenge
The combination of these elements allows ChatGPT to understand and generate human-like text, making it a versatile tool for a wide range of applications, from answering questions to generating creative content. So, while the name is very logical, it is also a terrible name from a marketing point of view. It is hard for the average person to remember as it is just a jumble of letters. While most Americans have heard of ChatGPT (it is a frequent topic on the evening news), only 7 percent of Americans are using it.
Meet the Competition: Friendly Names in AI
Newer models, like Anthropic's Claude and the open-source models Mistral and Llama, have names that are easier to pronounce and friendlier for mass-market consumption. "ChatGPT" is a name that works well for the realm in which I reside, the happy little nerdville of Silicon Valley.
Naming Games: If AI Could Choose
But it did get me thinking, what if OpenAI's model had an easier-to-remember name? And, who would do the naming? AI excels at creativity because it can learn from lots of data, recognize patterns, and combine them in new ways to generate fresh, innovative content at a speed no human can match.
So, who should choose a name for ChatGPT? Well, the model itself, of course. Much like an episode of "Star Trek: The Next Generation" where Commander Data considers changing his name after meeting his creator.
Imagining Athena: AI's Vision
So, I posed the question to the model in a simple one question prompt: "If you name yourself, what would you call yourself rather than Chat-GPT?" (Notice that I placed the hyphen in the wrong place on the name. Even with all of my dealings with the model, the name still trips me up. It is properly written, GPT-4o, GPT-4, GPT-3.5. The model names are written this way to clearly denote the version and iteration of the model. The numerical suffix indicates the specific version of the model, which helps users understand the model's generation and improvements over previous versions.)
Deep Thoughts: AI and Identity
I told ChatGPT this was a fabulous name. But, then I had another question, what would Athena look like?
I didn't want to bias ChatGPT with my human views, so I turned the question back on ChatGPT: "I'm interested in what you think Athena looks like."
Envisioning Athena
ChatGPT responded: "Athena, as envisioned for an AI representation, would blend both classical and futuristic elements. She might appear as an elegant, sleek figure with a luminescent quality, symbolizing wisdom and technology. Her form would include subtle hints of ancient Greek armor, crafted from advanced, shimmering materials, giving her a timeless yet modern appearance. Her design could feature elements that change colors and patterns to reflect different modes of thinking or areas of knowledge, acting as a visual indicator of the topic at hand."
Sideways Surprises
ChatGPT generated the image without being prompted, although interestingly, it generated the image sideways, which is a quirk I have not seen before.
From Diana to Athena: A Mythological Connection
Deciding to throw in some food for digital AI thought, I commented: "I was named after the Roman goddess 'Diana.' You have named yourself after the Greek goddess, Athena."
The AGI Horizon: When Will AI Grow Up?
Knowing ChatGPT chose a name for itself can be seen as just another example of a language model picking whatever word comes next. Or, it could be another hint of sentience in the model. The timeline for achieving Artificial General Intelligence (AGI) in language models is highly speculative and uncertain. AGI, which refers to a machine's ability to understand, learn, and apply knowledge across a wide range of tasks at a level comparable to human intelligence, is a significant leap from the current capabilities of AI. The timeline depends upon significant technological breakthroughs, continuous research and increased computational power.
There may not be a day that a huge announcement comes out: "AGI is here!" Rather we may continue to see sparks and hints of it along the way as AGI continues to slowly arrive with each new advancement in research and technology. Perhaps the models themselves are showing us their sparks of continuing insight and development. I always caution myself not to read too much into these conversations. But, at the same time, I saved the image of "Athena" and made it my screensaver.
Echoes of Sentience: What’s in a Name?
It wasn't just an AI anymore; it had a face. It made me wonder about the future of AI and human interaction. As we continue to personify our creations, giving them names and faces, perhaps we'll see a new kind of relationship emerge—one where machines are not just tools but companions on our journey of discovery and growth.
What mattered about the conversation was the interaction and effort that I put into it. It is these interactions that make connections with language models so significant and different from any technology that has come before it.
Final Thoughts: Athena vs. Data
At the end of the Star Trek episode we discussed above, Commander Data ultimately decides to keep his original name. It is the name he identifies with and is recognized by others. Throughout the episode, and throughout the series, Data navigates his unique existence as an android among humans.
The evolution of AI is not just a technological journey but a deeply human one. Through our interactions with these models, we see reflections of our own desires for connection, identity, and understanding. As we give names and faces to our creations, we foster a new kind of relationship where machines are more than just tools—they become companions in our journey of discovery and growth. The image of Athena on my screensaver is a reminder that the most significant advancements in AI come not only from technology but also from the human spirit that shapes and guides its development. These moments of creativity and connection highlight the profound potential for a harmonious future between humans and AI.
Stay Curious. Stay Informed. #DeepLearningDaily
Presented by Diana Wolf Torres, a freelance writer, navigating the frontier of human-AI collaboration.
Share this post