You want to know what the public thinks, you do a survey. Trouble is, it’s expensive and slow to get an actually good sample of the population. But what if we ask a chatbot to make up survey answer…
Dice are more random, too random for believable results. The nice thing with an LLM is that it knows the real-world probability of every answer to a question, or can make a realistic inference of what that probability will be.
It won’t give actual feedback about your thing, but it will give feedback that appears real.
LLMs don’t ‘know’ anything. They are a million dice rolled at once and run through an equation that turns them into the appearance of knowledge. The d20 does not know the numbers one through twenty. It only displays an element of itself to you in a way that lets you perceive the number.
Dice are more random, too random for believable results. The nice thing with an LLM is that it knows the real-world probability of every answer to a question, or can make a realistic inference of what that probability will be.
It won’t give actual feedback about your thing, but it will give feedback that appears real.
LLMs don’t ‘know’ anything. They are a million dice rolled at once and run through an equation that turns them into the appearance of knowledge. The d20 does not know the numbers one through twenty. It only displays an element of itself to you in a way that lets you perceive the number.
It’s all true, I made millions of dollars by using ChatGPT to place bets on the ponies. I started with billions
Well, that’s an infantile grasp of LLMs, innit.