Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

GitHub - barnoid/AIAI2: NaNoGenMo 2024 novel from AI captioned stills from the movie A.I. Artificial Intelligence

Dec 02, 2024 - github.com
The article discusses an experiment where the author uses an AI tool, LLaVA 1.5, to generate a novelization of the film "A.I. Artificial Intelligence". The author uses stills from the film as prompts for the AI, instructing it to write paragraphs and dialogues based on the images. Despite the author's instructions to avoid mentioning the image or describing it, the AI occasionally reverts to image description. The AI-generated text is found to be more coherent and novel-like than previous attempts, but also repetitive and often devolves into mundane business meetings.

The author concludes that the returns from using large language models (LLMs) like LLaVA are diminishing and that throwing more training data and power at them will not result in them achieving full sentience. The author also expresses doubt about repeating the experiment in the future, predicting that the results will become even blander. The author believes that AI was more amusing when it was less sophisticated and that a model that averages all the text on the internet will not produce anything better than average.

Key takeaways:

  • The author revisited their NaNoGenMo 2016 entry for NaNoGenMo 2024 using current AI tools to generate a novelisation of the film A.I. Artificial Intelligence.
  • The process involved ripping the DVD to a file, using ffmpeg to create stills, and using LLaVA 1.5 to generate text based on the images.
  • The resulting text was more coherent and novel-like, but occasionally reverted to image describing despite the author's insistence on not mentioning the image in the prompt.
  • The author believes that we're in the diminishing returns stage of large language models and that throwing more training data and power at them won't result in full sentience.
View Full Article

Comments (0)

Be the first to comment!