you are viewing a single comment's thread
view the rest of the comments
[โ€“] 0 points 1 year ago (4 children)

But an LLM as a node in a framework that can call a python library should be able to count the number of Rs in strawberry.

It doesn't scale to AGI but it does reduce hallucinations.

  • source
  • parent
  • hideshow 4 child comments
  • [+] 1 point 1 year ago* (2 children)
  • [โ€“] 1 point 1 year ago

    The claim is not that all LLMs are agents, but rather that agents (which incorporate an LLM as one of their key components) are more powerful than an LLM on its own.

    We don't know how far away we are from recursive self-improvement. We might already be there to be honest; how much of the job of an LLM researcher can already be automated? It's unclear if there's some ceiling to what a recursively-improved GPT4.x-w/e can do though; maybe there's a key hypothesis it will never formulate on the quest for self-improvement.

  • source
  • parent
  • [โ€“] 0 points 1 year ago

    The only thing worse than the ai shills are the tech bro mansplainaitions of how "ai works" when they are utterly uninformed of the actual science. Please stop making educated guesses for others and typing them out in a teacher's voice. It's extremely aggravating

  • source
  • parent
  • [โ€“] 0 points 1 year ago (1 child)

    You'd still be better off starting with a 50s language processor, then grafting on some API calls.

  • source
  • parent
  • hideshow 1 child comment
  • [โ€“] 1 point 1 year ago

    in what context? LLMs are extremely good at bridging from natural language to API calls. I dare say it's one of the few use cases that have decisively landed on "yes, this is something LLMs are actually good at." Maybe not five nines of reliability, but language itself doesn't have five nines of reliability.

  • source
  • parent
  • load more comments (-1 replies)