I am amazed by the ease with which an LLM like ChatGPT can come up with random “ideas” – initially the LLM picks one token in a probability distribution of tokens, then it repeats this operation for the next token, etc., and in the end you get a random “thought” from a distribution of phrases that can be responses to the prompt.
I experimented on this with something trivial – picking a recipe randomly:
I said:
suggest a recipe for tonight, give me just the title and one sentence description
ChatGPT said:
Lemongrass Tofu with Coconut Noodles — silky tofu and fresh noodles tossed in a light coconut-lime sauce infused with lemongrass and ginger.
I said:
suggest a recipe for tonight, give me just the title and one sentence description
ChatGPT said:
Honey-Soy Glazed Salmon — oven-baked salmon fillets coated in a sweet-salty glaze with ginger, garlic, and a touch of sesame oil.
I said:
suggest a recipe for tonight, give me just the title and one sentence description
ChatGPT said:
Creamy Tomato Basil Pasta — a quick, comforting dish with ripe tomatoes, garlic, and fresh basil folded into silky cream sauce.
I said:
suggest a recipe for tonight, give me just the title and one sentence description
ChatGPT said:
Carrot and Ginger Soup — a bright, velvety soup with fresh ginger and a hint of orange for warmth and freshness.
To be continued…
Na va-nad 
Leave a comment