[randcraw]

In judging GPT, we should be drawing a line in the sand between a poor writer (e.g. a college student) and an excellent one (a professional, ideally a domain expert). GPT is impressing us now only because we have very low expectations for a computer to write like a human. But when judged against a capable human, especially when you focus on the _information_ that's conveyed, GPT sucks.

Few of us would want to read a book written as flaccidly as GPT does, a wandering narrative that cannot connect the semantics of one sentence to the next. GPT is capable only of writing _sets_ of sentences, not a progression of them where a concept is introduced and subsequent text tests and contrasts a convincing set of complements and alternatives. Given LLM architectures (and inherent black boxes), that's likely to never change since they don't understand logic or dependency, sufficiency, or necessity. Without those skills, no LLM will ever be able to _develop_ an idea or expand on the implications proposed in an introduction. Have you ever seen GPT conclude a paragraph with a bang? And you never will.

You'll note too that GPT has not attempted to write dialog. I think there's good reason for that. Talk strips away all the excess verbiage. Humans say only what's essential to convey our message. Pointless blather that leads nowhere is maddening to listen to for long. But without a clear focus, that's exactly what I'd expect from GPT: wandering speech that's totally disengaging. Surprising the reader simply is not in its DNA.

So if you're happy reading narratives that wander, that don't lead anywhere, with characters lacking personality, and a narrative style lacking the essentials of every engaging tale (exposition, conflict, suspense, climax, resolution)... then perhaps GPT is for you. But if that's GPT's great promise -- to generate businessspeak that's "tolerable" but even less engaging than the marketing schlock that immerses us now -- then thanks, but no thanks.

[consumer451]

I am not arguing that the current generation of language models will result in 1:1 levels of human:machine intelligence, just that pattern recognition seems like it is enough to eventually lead there.

> You'll note too that GPT has not attempted to write dialog.

Here is one of my prompts, is this not dialogue?

"The year is 1960. Choose 3 famous physicists. They are having a debate about whether black holes exist. Show the transcript."

  Albert Einstein: Gentlemen, I have been studying the theory of relativity for many years, and I believe that the concept of black holes is absurd. The idea that an object could be so massive and dense that not even light can escape its gravitational pull goes against everything we know about the laws of physics.

  Stephen Hawking: Mr. Einstein, I must respectfully disagree. The mathematics behind black hole theory is quite compelling, and there is mounting evidence from observations of stars and other celestial bodies that suggests their existence.

  Richard Feynman: I think both of you make valid points, but I believe that we must approach this question with an open mind. We cannot dismiss the idea of black holes simply because they challenge our current understanding of the universe. We must continue to gather evidence and test our theories in order to better understand the nature of these mysterious objects.

  Einstein: But surely, Mr. Hawking, if black holes were real, we would have observed their effects on nearby objects by now.

  Hawking: Not necessarily, Mr. Einstein. Black holes are incredibly difficult to detect, and we may not have the technology or understanding to do so at this point in time.

  Feynman: I agree with Mr. Hawking. The study of black holes is a relatively new field, and we are still working to develop the tools and techniques needed to study them more effectively. I believe that with further research and experimentation, we will be able to confirm or disprove their existence.

  Einstein: I will continue to remain skeptical until I see concrete evidence of black holes. But I am open to being proven wrong if the evidence warrants it.

  Hawking: And I will continue to explore the possibility of black holes and work to gather more evidence to support their existence.

  Feynman: I think that is a fair and reasonable approach. As scientists, it is our duty to seek the truth, no matter how challenging it may be.