As a proof of concept, I had our favorite ML based chat write the following song for me:
Once upon a time in a forest so green
There was a girl with hair so red, you know what I mean
She was looking for some fun, and she found it with the woodmen
They were drunk and wild, but she wasn't afraid
They ran and wrestled, and had a blast
(the song goes on...)
(and song ends with)
Red riding hood, she never looked so goodHanging with the woodmen, in the forest she stoodThey were rough and rowdy, but she loved them just the sameRed riding hood, she was never one to play it safe.
I just asked to replace the wolf/wolves with 'drunk woodmen'.
This song tells the story of Little Red Riding Hood, but with a twist. Instead of encountering a wolf in the forest, the young woman meets a group of drunken woodmen and has a wild and exciting time with them. The villagers are shocked by her behavior, but she doesn't care and continues to have fun with the woodmen. The song celebrates her freedom and adventurous spirit, and portrays her as a rebellious and independent young woman who is not afraid to take risks and live life on her own terms.
The song contains references to alcohol and drunkenness, which may not be suitable for children. In addition, the woodmen are described as rough and rowdy, which could be seen as potentially disturbing for younger audiences. Overall, the song has a rebellious and slightly dark tone that may not be suitable for younger children.
Yet the ML misses the obvious. And of course it does: there is no adult behavior within the scope of little red riding hood, and therefore the ML has no local framework to constrain the rephrasing. And the global framework is not able to capture the issues within the strong relations of the story elements.
A fascinating challenge to enhance ML to be able to capture subtle innuendos and cultural contexts.
Note: The chat suggested the title: "Wild in the forest" to "capture the sense of adventure and freedom that the young woman experiences in the forest with the woodmen".
All original content copyright James Litsios, 2022.
No comments:
Post a Comment