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

The revolt of the reader

bcantrill.dtrace.org

Post reply on HN
Print view View original

171–180 of 313 posts

Re: The revolt of the reader

#171

Post by AnimalMuppet »

Ygg2 wrote: post #164
ahepp wrote: post #151

Earlier quoted context omitted.

A bigger question I'm interested in is why do LLMs speak like that in the first place? Is that really what you get if you took the average of the English language? It would be difficult for me to believe that. Is there something about tuning for desirable qualities that forces LLMs to have this voice?

Not average of English. Average of all written text. Which probably includes lots of marketing and hypetexts.

And The New Yorker - writing that is written to sound impressive, and takes forever to get to the point. I hated that kind of writing in The New Yorker long before LLMs made it cool to hate that.

Re: The revolt of the reader

#172

Post by AnimalMuppet »

lljk_kennedy wrote: post #133
jimmaswell wrote: post #117

Earlier quoted context omitted.

The second one was very clear and to the point. Parsing it was rewarded with instant understanding and I enjoyed the word choice. The first one was just annoying; I could tell it was just listing a bunch of pointless analogies to try to make its point sound more grandiose so I immediately started skimming, and didn't come away feeling like it meant much other than "we all die in the end". The second one made an actua…

The first communicated a feeling. A brief flutter in the soul of a picture of recognition, painted for your mind's eye with care by the author. The second transcribed considerable information bandwidth through intentionally structured word choice for maximal density.

Yeah. The first one was like a minimalist painting, the second like a software specification.

I'm pretty sure that the general public does not want to read software specifications.

Re: The revolt of the reader

#173

Post by AnimalMuppet »

Barbing wrote: post #94
Kerrick wrote: post #93

Earlier quoted context omitted.

Other translations keep Zinsser's preferred lack of fuzz but avoid using "is ... to" for possession. For example, the Lexham English Bible: > I looked again and saw under the sun that the race does not belong to the swift, the battle does not belong to the mighty, food does not belong to the wise, wealth does not belong to the intelligent, and success does not belong to the skillful, for time and chance befalls all o…

Easiest! Loses some color, gains much clarity.

Color. Perfect word; thank you. That's what LLM writing doesn't have, and the second version didn't have it either.

Re: The revolt of the reader

#174

Post by kccqzy »

SSLy wrote: post #136
kccqzy wrote: post #35

I would love to use Pangram but they simply don’t allow signing up with my custom email domain. The error was “This email address can't be used for signup. Please use a different email.” I’m not about to create a Gmail is to use your service. To me the attack on the decentralized nature on Internet infrastructure is no less serious than the attack on the human provenance of writing itself.

Weird. I have recently created an account on my meme domain ($something.party) just fine.

Huh. Very weird. Today I decided to put in a fake Gmail address that I did not own and I got the same error. Perhaps they did not like my residential IP.

Re: The revolt of the reader

#175

Post by emmelaich »

esjeon wrote: post #120
kierangill wrote: post #65

My revolt is against the cognitive stress of reading generated text. A trope typically indicates I’m in for an uphill read. I recently read this William Zinsser quote that inspired a nickname for this: Clotted Claude [1]. > Nobody has made the point better than George Orwell in his translation into modern bureaucratic fuzz of this famous verse from Ecclesiastes: > > I returned and saw under the sun, that the race is…

I think Orwell did a great job there actually. Despite its bizarre look, the sentence is evocative and eloquent. It does make me get a clear mental image from the very first word. It leaves little room for roaming and guessing, as it firmly nails elements one by one, and, by the time I reach the end of the sentence, I get the full meaning almost immediately. This sentence is not randomly written; this is crafted with…

Are you sure you're referencing the correct quote? Are you familiar with original? Did you you use AI to write this comment?

Re: The revolt of the reader

#176

Post by layer8 »

tdeck wrote: post #68
kierangill wrote: post #65

My revolt is against the cognitive stress of reading generated text. A trope typically indicates I’m in for an uphill read. I recently read this William Zinsser quote that inspired a nickname for this: Clotted Claude [1]. > Nobody has made the point better than George Orwell in his translation into modern bureaucratic fuzz of this famous verse from Ecclesiastes: > > I returned and saw under the sun, that the race is…

Am I the only one that finds the second one much easier to parse?

You’re not. The first is vague and requires significant interpretation, the second is very clear and to the point in what it’s saying.

Re: The revolt of the reader

#177

Post by Alwayshasbeeb »

conmod278 wrote: post #113
pshirshov wrote: post #95

> do you think readers can’t tell? No. I have good anecdata: readers cannot reliably distinguish my own prose from LLM-written one apart from cases where LLMs use odd metaphors or one of their specific patterns. I've been specifically experimenting with that.

https://schwitzsplinters.blogspot.com/2022/07/results-comput... Schwitzgebel, Strasser, and Crosby fine-tuned GPT-3 on Dennett's corpus and asked whether readers could pick Dennett's real answers to ten philosophical questions from four machine-generated alternatives, with no cherry-picking beyond mechanical length filters. Even Dennett experts averaged only 5.1 out of 10 (well below the 80% the authors predicted), b…

>Schwitzgebel, Strasser, and Crosby fine-tuned GPT-3 on Dennett's corpus

This sounds like a completely different scenario. How many users who post LLM written blog posts are tuning the weights of their LLMs on a large corpus of their own original writing? I wouldn't doubt that this produces far more convincing and pleasant output than the disgusting slop from out of the box Claude.

Re: The revolt of the reader

#179

Post by HappyPanacea »

classified wrote: post #165
ahepp wrote: post #160

I was so optimistic about using LLMs for "write once, read many" English language documents, but the more I've used the tools, the more pessimistic I get. More and more, I try to ask it for low prose responses because its writing just seems like such a low signal to noise ratio I'm curious about why LLM writing fails. Particularly whether LLM writing is fundamentally flawed, or if it's just distinctive and since it o…

> I'm curious about why LLM writing fails. Apart from the tasteless manipulations of the providers, it's mostly training data. LLMs output the average of their training data, and the overwhelming majority of humans are bad writers.

This argument doesn't work, the average majority of humans are bad at math but recent LLM aren't.

Re: The revolt of the reader

#180

Post by grey-area »

esjeon wrote: post #120
kierangill wrote: post #65

My revolt is against the cognitive stress of reading generated text. A trope typically indicates I’m in for an uphill read. I recently read this William Zinsser quote that inspired a nickname for this: Clotted Claude [1]. > Nobody has made the point better than George Orwell in his translation into modern bureaucratic fuzz of this famous verse from Ecclesiastes: > > I returned and saw under the sun, that the race is…

I think Orwell did a great job there actually. Despite its bizarre look, the sentence is evocative and eloquent. It does make me get a clear mental image from the very first word. It leaves little room for roaming and guessing, as it firmly nails elements one by one, and, by the time I reach the end of the sentence, I get the full meaning almost immediately. This sentence is not randomly written; this is crafted with…

Read some Orwell: https://www.orwellfoundation.com/the-orwell-foundation/orwel...
Post reply on HN