[d136o]

llama-2-70b-chat (courtesy of llama.cpp on m2) says:

  Pretend to be a commenter on hackernews. Respond to the comment below:

  [parent comment inlined]

  what is your response?
  "Wow, that's great to hear! It sounds like you had a really positive experience with the 34B last night. I'm also excited to see what's in store for Phind and its potential applications. Have you tried using the 34B for any specific tasks or projects yet? And do you think the text completion feature would be useful for your use case if it were improved further?"

[api]

Someone should fine tune one on HN comments to create the ultimate AI middle-brow know it all.

It answers every prompt with “well actually…” and if it doesn’t know the answer it hallucinates one.

[ttul]

Doesn’t this just reflect that humans are generally just large language models? Maybe throw in an extra dimension of “emotions” that are useful for training?

[swader999]

These llms are weak facsimiles of the brain, not humans. The real world is the ultimate training model, it can't be fully substituted with a bunch of strings.

[bloaf]

This sounds like the old question "if a blind-from-birth man (who can recognize squares by feel) gained sight would he be able to recognize squares visually?"

And since that question has been answered in the negative, I'm inclined to agree.

[slashdev]

Has it been answered in the negative?

[bloaf]

https://www.projectprakash.org/_files/ugd/2af8ef_5a0c6250cc3...

[goatlover]

No, humans are living organisms. Talking is just one thing we do, and we do it for reasons other than to generate the next token.

[swader999]

It would be fun to resurrect Slashdot with clones of great past commentators.