Wrt. this feeling you're describing here: You might mostly be feeling the Enshittification. At least that's a big thing for me. Companies are not making things better, they are making everything worse. Instead of actually making new stuff, they're wringing the existing lemon five extra times to squeeze that last drop of juice out of it, adding one extra ad in the youtube viewing, making it harder to integrate. APIs being deprecated, walled gardens. Things have been going downhill for at least a decade. This makes me sad.

Comments URL: https://news.ycombinator.com/item?id=41950032

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=40508797

Points: 28

# Comments: 10

I feel you can even see this when you ask it certain questions with “think in steps” prompting: It can output temporary thoughts which aren’t of use in the final answer - again just as we do when attacking a problem we can’t immediately answer.

Also, we humans often use pen and paper to jot down temporary and intermediary thoughts and answers. Again, LLMs don’t have that, but can use the output as something similar.

Some styles of ToT prompting actually make the LLM have two types of output - one for its “inner voice thinking”, and then another for output meant for the human. The same goes when one give the LLM method calling abilities, or “googling”: This can be seen as a way to perform thinking and reasoning without output meant for the user, before formulating an answer.