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

The computers are getting better at writing

newyorker.com

Post reply on HN
Print view View original

91–100 of 165 posts

Re: The computers are getting better at writing

#91

Post by yesenadam »

WesolyKubeczek wrote: post #90

I have a suspicion that, since GPT-3 gorged its enormously swollen fuzzy digital belly on a lot of real prose, it might, when prompted, occasionally throw in a piece of the prose in question, or a whole original passage, because to its fitting function, it would be a suitable thing to do. But then again, aren’t we all doing the same, regurgitating bits and pieces that we heard or read before and liked? Don’t we all s…

> Don’t we all sometimes, when busy with our own thoughts and worries, occasionally spout out oddly appropriate responses to what our spouses are speaking, without actually listening to and processing the conversation, maybe because we heard it all so many times we can readily predict what they are going to say?

Uh.. no, not me. That sounds very strange to me, and sad. I always listen to everything she says. And expect the same back. Otherwise it wouldn't be a good relationship, I think. (Maybe I'm super-naïve!..or something.)

Re: The computers are getting better at writing

#92

Post by camillomiller »

Al-Khwarizmi wrote: post #73
thaumasiotes wrote: post #63

Earlier quoted context omitted.

> It means we can express concepts in English with structures and flows that, if grammatically correct, have the advantage of sounding original, different, sometimes exotic. Yeah, that happens all the time. It always strikes me as unfair when someone comes out with an ostensibly perfect sentence and the result is "well, you didn't make any mistakes; all the words mean what you want them to mean and all the grammar is…

It's useful to learn how they say it, though. Not because we should pretend to be native speakers when we aren't, but because language is more efficient if you know the expected way to use it. The correct but awkward sentences from non-natives (I also use them, being a non-native English speaker) will more easily get lost in situations with background noise, several people talking, people not paying a lot of attentio…

True, but OP was asking for an AI tool to help in this. I think the language bias on such a tool would be enormous, and it would contribute to flatten a piece of writing. Being effective by saying things the right way, or picking the right words to express a specific context, is definitely important. My point was this: once you get to a good-enough point, what you're looking for is an editor (of sorts, not necessarily a professional one). Someone that could recognize how your idiomatic choice of words serves the piece right, or makes it harder to understand. What really helped me was asking native friends to read my posts or my articles, and tell me what they were getting from them. After a while, through this process, you'll get better yourself at recognizing these patterns. Before that, I worked hard on understanding the specific pitfalls of writing in English as a native Italian. One clear example: attributive nouns.

Re: The computers are getting better at writing

#93

Post by claudiawerner »

WesolyKubeczek wrote: post #90

I have a suspicion that, since GPT-3 gorged its enormously swollen fuzzy digital belly on a lot of real prose, it might, when prompted, occasionally throw in a piece of the prose in question, or a whole original passage, because to its fitting function, it would be a suitable thing to do. But then again, aren’t we all doing the same, regurgitating bits and pieces that we heard or read before and liked? Don’t we all s…

>Don’t we all sometimes, when busy with our own thoughts and worries, occasionally spout out oddly appropriate responses to what our spouses are speaking, without actually listening to and processing the conversation, maybe because we heard it all so many times we can readily predict what they are going to say?

No. Sometimes I can predict what a friend will say but I won't actually say it. The more I think about it, the more I realise that AI at the moment is the unlistening (but hearing) spouse. And just like it seems we can engage with such a person (though can only rarely), so too can the AI trick us ('simulate') that behaviour.

Re: The computers are getting better at writing

#94

Post by sunshineforever »

Animats wrote: post #35
lbacaj wrote: post #3

I have been doing a lot of writing lately, short and longer essays. I have also written on-and-off for the last ten years. Writing well is not easy. I used to think I wrote well until I started reading better writers. The whole idea that we will just slap together a bunch of text using some “AI” and it will resonate with people is crazy to me. As an engineer whose dabbled with some AI and ML, and has even seen what G…

we are as far away from being able to use AI to write a best seller as we are from landing on the Sun. Harlequin Romances, though, those little soft-core porn pamphlets for women found at supermarket checkouts, could probably be generated. There are about 4,000 of them, and they're written to a set formula - “Boy meets girl, boy loses girl on page 56, and, by page 180, the book would end with a marriage proposal.” Lo…

Yes, when signing up for the beta I almost included 'eroticc but I thought better of it.

Re: The computers are getting better at writing

#95

Post by goodpoint »

caconym_ wrote: post #66

The lesson we should take from GPT-3 is that we spend way too much time reading text that isn't really saying anything, and/or failing to find meaning in what we read. It's a neat trick, and I think it could absolutely replace much or most of the writing on the internet today. But is it good writing? No, not really. At least, not in the sense of writing as producing anything more substantive than slick prose with a v…

Many (human-written) books and articles are 10% content and 90% fluff and repetition. The articles shared on HN are a good example.

If the goal is to increase the SNR, GPT-3 is probably not going to help.

Re: The computers are getting better at writing

#96

Post by sunshineforever »

watwut wrote: post #64
dumpsterdiver wrote: post #42

Earlier quoted context omitted.

Well, it's not just women, I have read and enjoyed such writing. But you are correct, writing that lacks substance intended for people who expect nothing more. Sex is easy to write about. It doesn't take much to turn people on.

I used to read a lot of junk paperbacks - mostly horrors, but also stories about truck drivers, detectives and western stories. They were schematic to the extreme. Looking back, it was the same story over and over and over. I liked them back then. I used to read also a lot of repetitive sci-fi: those small start trek books. I never read Harlequin, but it being repetitive is not something special. Back when people rea…

Junk paperbacks about truck drivers sound interesting... Remember any titles?

Re: The computers are getting better at writing

#97

Post by sunshineforever »

anthk wrote: post #85
watwut wrote: post #64

Earlier quoted context omitted.

I used to read a lot of junk paperbacks - mostly horrors, but also stories about truck drivers, detectives and western stories. They were schematic to the extreme. Looking back, it was the same story over and over and over. I liked them back then. I used to read also a lot of repetitive sci-fi: those small start trek books. I never read Harlequin, but it being repetitive is not something special. Back when people rea…

>I used to read a lot of junk paperbacks - mostly horrors, but also stories about truck drivers, detectives and western stories. They were schematic to the extreme. He, ditto in Spain. In most cases the (same) authors would rehash a detective story as some sci-fi based short novel by just changing some devices and lore and call it done. Well, in the end cyberpunk it's just futuristic noir.

Dan brown seems to do this. Da Vinci code, angels and demons, and the one about the NSA all have the same plot structure.

Re: The computers are getting better at writing

#98

Post by jcims »

Smithalicious wrote: post #81
bertil wrote: post #69

Earlier quoted context omitted.

If you want to echo the last paragraph of the article, the system also doesn’t know when to stop. Which leads to a simple improvement: teach the model when to stop, what sections to remove. There’s already great ML-based summary engines, and systems able to answer questions from descriptions.

I wonder if that could be a viable approach, having a separate "writer" and "editor" AI

I do the same thing when I write (except for my comments on HN lol)

GPT-3 reads like the unfiltered garbage that comes out of my head when I'm trying to get ideas out. The primary difference is that I have empathy for the audience so I go through the effort to reread, clean it up, clear it up then cut it down.

But that secondary editing process has nothing to do with the subject matter or initial content generation process. It was trained through years of *not* doing it and having my audience ask lots of questions and clearly misunderstand what I was trying to say (let's call it reinforcement learning). As a result I now have an intuition about which concepts need explanatory analogies, based on my understanding of what the readers know, and which are almost certainly going to be understood outright. I think this gets at the root of the difference.

Basically when I write, I'm not trying to generate text, I'm trying to generate training data that will amend foreign models with a high fidelity representation of a subset of mine.

This feels GAN-like but different. It's like you need to have two separate models, the 'expert' and the 'n00b' (or ten n00bs trained on different data), ask both of them the same thing, and one-shot retrain the n00b from the answers provided by the 'expert' until the n00b is able to generate content that the expert finds to be sufficiently similar.

Re: The computers are getting better at writing

#99

Post by causality0 »

Digit-Al wrote: post #67
causality0 wrote: post #8

Earlier quoted context omitted.

The better question is, would you read anything else? What happens when we can just dial up the story we want? What happens when these models combine the skillfulness of a human writer with the command of facts, theories, behaviors, and lore of computer records? Imagine. You could feed it all of Tolkien's writings and tell it to give you an epic saga of novels set in the First Age of Middle Earth. You could tweak a p…

Don't you think there's a danger you'd end up with stories that looked like JRR Tolkien as written by George RR Martin?

I mean, maybe if I was running GPT-3 on a Raspberry Pi.

https://www.youtube.com/watch?v=oShTJ90fC34

Re: The computers are getting better at writing

#100

Post by anthk »

sunshineforever wrote: post #97
anthk wrote: post #85

Earlier quoted context omitted.

>I used to read a lot of junk paperbacks - mostly horrors, but also stories about truck drivers, detectives and western stories. They were schematic to the extreme. He, ditto in Spain. In most cases the (same) authors would rehash a detective story as some sci-fi based short novel by just changing some devices and lore and call it done. Well, in the end cyberpunk it's just futuristic noir.

Dan brown seems to do this. Da Vinci code, angels and demons, and the one about the NSA all have the same plot structure.

Just copycat Broken Sword so nobody notices anything.
Post reply on HN