Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Margaret Atwood Reviews a Margaret Atwood Story by AI

thewalrus.ca

Post reply on HN
Print view View original

61–70 of 79 posts

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#61

Post by jacquesm »

CamperBob2 wrote: post #37
jacquesm wrote: post #35

Earlier quoted context omitted.

Wrong thread?

Coders use the best data structure to solve a problem not for the users but for another coder to appreciate. I find that sentiment mildly offensive. I write a lot of code myself, but for every program I write, I use a hundred programs written by other people. If those programmers want to impress me, they will keep my needs as a user in mind, not their own egos.

I don't know how much code you usually read but from my experience seeing coders using the best data structure to solve a problem for other coders to appreciate is very rare, and it isn't rare because they're doing it for the users, it's rare because they are not doing it at all. The bar seems to be 'produces the expected output' not 'best'.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#62

Post by flenserboy »

HPsquared wrote: post #21
flenserboy wrote: post #15

Are there any turnkey engines designed to run locally which can be trained on your own data? I've been itching to put my work into one, just to see what the results might be.

Llama 2 and various derivatives as the model. Get quantized models from https://huggingface.co/TheBloke Oobabooga text-generation-webui for the server. In the interface, use ExLlama for GPU inference (fast; for smaller models which fit in VRAM). Llama.cpp for large models (higher fidelity but slower), CPU+GPU. 13B parameter 4-bit quantized model (type 'GPTQ") can fit in a 12GB RTX 3060. 24GB card (e.g. a 3090) needed…

Much appreciated!

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#64

Post by seanthemon »

inciampati wrote: post #56
FrustratedMonky wrote: post #14

Earlier quoted context omitted.

Yes When I have a conversation with GPT4, it keeps the history, and the entire history is a prompt for the next prompt. I would say, not totally unlike a human memory. just GPT4 is limited to 8000 characters or something. Humans have a bit more, but with added 'forgetfulness', so who knows how many characters for real. Humans don't actually recall perfect text very well.

But we do manage to remember stuff that happened "quadrillions" of tokens (of sensory input) back. Sure, we are wrong a lot, but we have a context that goes way back. A LLM has a fruit fly's version of what we work with, although in some versions it has perfect recall in that context.

Or it can be said that we boil down our experience to a few millions of tokens, only a set of experiences, emotions and often wrong/made up memories.

Your comment assumes a human can recall all (potentially incorrect) memories and use those to make some judgement, but fact of the matter is we don't.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#65

Post by mewpmewp2 »

datameta wrote: post #42
muglug wrote: post #38

Earlier quoted context omitted.

> the best model is at least 10x smarter than the free version of ChatGPT Citation needed. What does 10x smarter mean here? There’s an ongoing debate about whether the word “smart” even applies to a text prediction engine.

My gut metric says it's a ~20% increase in perceived interpretation and output complexity, whatever that means exactly. But there are plenty of eval result aggregators out there.

To me GPT-4 seems actually intelligent and reasoning capable while GPT-3.5 does not. Many of my usecases involve giving large bodies of text to GPT and asking to reason about this. 3.5 has no clue, but 4 seems to handle it intelligently.

Overall it is as if GPT3.5 feels just like a clueless summarizer, but GPT4 intelligent interpreter and reasoner that I can trust.

Depending on which way you look at it, it could be 10x or 1000x the intelligence.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#66

Post by datameta »

mewpmewp2 wrote: post #65
datameta wrote: post #42

Earlier quoted context omitted.

My gut metric says it's a ~20% increase in perceived interpretation and output complexity, whatever that means exactly. But there are plenty of eval result aggregators out there.

To me GPT-4 seems actually intelligent and reasoning capable while GPT-3.5 does not. Many of my usecases involve giving large bodies of text to GPT and asking to reason about this. 3.5 has no clue, but 4 seems to handle it intelligently. Overall it is as if GPT3.5 feels just like a clueless summarizer, but GPT4 intelligent interpreter and reasoner that I can trust. Depending on which way you look at it, it could be 1…

I think trust is a key thing you've hightlighted. I find myself doubting GPT3.5, whereas not at all for GPT4.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#67

Post by tkgally »

dools wrote: post #31

The Weeping Willows of Winnipeg is a shit story, but if you were working on a short story, and you got 5 suggested rewrites for a given paragraph, or you were looking for ideas for a plot point or something similar, then you could use ChatGPT to help you out. In exactly the same way, sometimes I give ChatGPT a complete coding task and it can't do the job. But while I'm working on code I can get it to do certain thing…

My current job maps in that direction--translation and writing. Lately I have been using GPT-4 to produce first drafts. It saves me time and effort and gives me ideas for expressions that I wouldn't have thought of on my own. It's also good for writing in genres that are not my strongest. I wrote a PR brochure recently, and GPT-4's drafts had more advertising punch than what I usually produce.

I still spend a lot of time polishing the final version, so the time savings are only about twenty percent.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#69

Post by otabdeveloper4 »

CamperBob2 wrote: post #36
bglazer wrote: post #16

Earlier quoted context omitted.

Even if there weren’t stylistic and logical problems with the story, I don’t think I’d be terribly interested in reading it. Fundamentally, literature is about communication with other people, living in another person’s mental world or understanding their unique perspective. It’s not really clear to me what human value an LLM generated story has. It’s a statistically probable sequence of tokens generated from the dis…

What do I learn from that? That you are nothing special. The computer is just doing what you do, putting one word after the last one. Picking each word more or less carefully, based on its own training and the audience's expectations. It's doing it badly, for the moment. But would we mock a talking dog who stutters? How is my life enriched? Being able to see what's coming is helpful, more often than not.

The LLM isn't creating new information, only packaging existing information.

Re: Margaret Atwood Reviews a Margaret Atwood Story by AI

#70

Post by rsynnott »

danenania wrote: post #34

I wonder which model was used for this? Based on the poem taking "10 seconds" to generate, I'd guess the free version of ChatGPT, meaning 3.5 turbo. While I wouldn't expect Atwood's conclusions to change too much by using GPT-4 instead, I think it's interesting that even the majority of educated people and journalists outside of tech don't seem to realize that the best model is at least 10x smarter than the free vers…

> think it's interesting that even the majority of educated people and journalists outside of tech don't seem to realize that the best model is at least 10x smarter than the free version of ChatGPT

I mean... the content-free drivel they generate is more _polished_, possibly, though I'm not sure this is actually an improvement. What do you mean by 'smarter', here?

Post reply on HN