A guide to the useful things one can do with LLMs.
To write stuff: nothing comes "even close to GPT-4... access at Bing for free or ... subscription to ChatGPT... GPT-3.5 also good and much faster". Some tips:
Make images: Midjourney is best: "lowest learning-curve ...just type in "thing-you-want-to-see --v 5"" (v5 specifies the latest model). Stable Diffusion is the open-source option (Bing (Image creator) requires signup).
There are biases: "use this explorer to see these biases at work", and they're "trained on existing art ... not transparent and potentially legally and ethically questionable."
Create ideas: To have good ideas you need a lot of ideas, so AI is perfect: "Will all these ideas be good or even sane? Of course not. But they can spark further thinking on your part". ChatGPT's the best option. Here is a guide.
Make videos: "It is now trivial to generate a video with a completely AI generated character... reading a AI-written script, talking in an AI-made voice, animated by AI". Deeo fake heaven. Use D-iD for animation, ElevenLabs for voice cloning.
Code: "GPT-3.5 is a powerful coding companion. But GPT-4 is next-level."
Self-learn: Use "as a jumping-off point for your own research, not as the final authority on anything."
More Stuff I Like
More Stuff tagged ai , guide , deep fake , llm
See also: Digital Transformation , Innovation Strategy , Science&Technology , Large language models