679
AI in reality (slrpnk.net)
submitted 2 years ago* by to c/programmer_humor@programming.dev
113 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 2 years ago (2 children)

How does conversation context work though? Is that memory not a form of learning?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 5 points 2 years ago* (1 child)

    The context window is a fixed size. If the conversation gets too long, the start will get pushed out and the AI will not remember anything from the start of the conversation. It's more like having a notepad in front of a human, the AI can reference it, but not learn from it.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 3 points 2 years ago

    Also, a key part of how GPT-based LLMs work today is they get the entire context window as their input all at once. Where as a human has to listen/read a word at a time and remember the start of the conversation on their own.

    I have a theory that this is one of the reasons LLMs don't understand the progression of time.

  • permalink
  • fedilink
  • source
  • parent