On a similar vein, I tried to get chatgpt to play wordle. The result looked something like:
Me: crane
GPT: _ _ _ _ e
Me: moist
GPT: _ _ _ r _
Me: glyph
GPT: you guessed it, the word was glyph
Now, maybe GPT 4 or other future developments will give better results, but to me this highlights exactly what you're saying. LLMs do not have an internal structure in their 'minds' that they're pondering about. It's a very impressive engine for guessing the next character to produce into a stream.
There's definitely usages for this, but not what a lot of people are saying.
Me: crane
GPT: _ _ _ _ e
Me: moist
GPT: _ _ _ r _
Me: glyph
GPT: you guessed it, the word was glyph
Now, maybe GPT 4 or other future developments will give better results, but to me this highlights exactly what you're saying. LLMs do not have an internal structure in their 'minds' that they're pondering about. It's a very impressive engine for guessing the next character to produce into a stream.
There's definitely usages for this, but not what a lot of people are saying.