Using generative large language models for visualization tasks
ChatGPT cannot output visual content. Its understanding of visual elements come from textual data describing different visual elements such as navigation bars, hero sections, or tables. While this can be effective in building good looking UI elements, you should expect some limitations in this domain. We will go through various visualization use cases in detail in the Visualizatn domain.
Comparing that to a dedicated ASCII art generator:
Even when prompted for a more detailed version, ChatGPT's visualization capabilities are currently limited.
This ASCII art includes more detail, such as feathers, claws, and a beak. ASCII art can range from simple designs to highly detailed and intricate artwork. It's a fun and creative way to express oneself using only the keyboard.
And when we ask GPT-4, we get a more honest response that it is limited in it's ability to generate ASCII art, but the art provided is more accurate.
Unfortunately, creating an extremely detailed owl using ASCII characters is beyond the scope of what I can provide within this text format. However, I can provide you with a simpler ASCII owl and a caption for it. You can always look for more detailed ASCII art online or use an ASCII art generator tool to create one.
Here's a simple owl in a markdown code block with a caption: