ChatGPT makes generating these text representations of media really approachable. It would be great to have a list of things to try with it along the lines of music programming with Glicol, graphs with MermaidJS, and graphics with TikZ.
To me it seems like an obvious thing to do: it makes for more maintainable assets, and it can speed up iteration cycles if you are trying to get a the logicial, relational elements of the diagram right.
I would argue here that this might be great now, but might not be maintainable in the long run. First, to generate new diagram description, one has to be online and connected to chatgpt. Second, if chatgpt api changes, one won’t be able to generate new diagrams from text without first fixing the access issues.
Ha, people are finally catching on! My first “real” use of ChatGPT was generating TikZ.
ChatGPT makes generating these text representations of media really approachable. It would be great to have a list of things to try with it along the lines of music programming with Glicol, graphs with MermaidJS, and graphics with TikZ.
Riley Goodside on Twitter was doing a lot of this stuff with GPT-3 last year.
I would argue here that this might be great now, but might not be maintainable in the long run. First, to generate new diagram description, one has to be online and connected to chatgpt. Second, if chatgpt api changes, one won’t be able to generate new diagrams from text without first fixing the access issues.