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

211–220 of 311 posts

Re: The revolt of the reader

#211

Post by grey-area »

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…

Lack of taste, intent and intelligence.

This is ok in domains if you can train against known good answers and make sure the machine generates conforming text most of the time. It falls apart in fuzzier domains where training is much harder and intent is required (i.e. having something to say).

LLM writing is generally ok in factual domains where it can regurgitate bits of wikipedia or answers to questions, they are terrible at long form writing, in particularly in literary styles, because of a lack of intelligence and taste.

I don't think the answer lies in the data or in their training. It seems we've had a few years for this problem to be solved, but nobody seems to have worked out an answer to it.

Re: The revolt of the reader

#212

Post by squidbeak »

mrob wrote: post #134
sltkr wrote: post #78

Earlier quoted context omitted.

Orwell's entire essay (Politics and the English Language) is well worth reading if you haven't before: https://www.orwellfoundation.com/the-orwell-foundation/orwel... (I'm guessing Zinsser's comments are from "On Writing Well", which you can also find online even though it is still under copyright.) It's a bit of a pet peeve when people include quotes on a blog post without linking or otherwise references their sourc…

But Orwell's rule 4 should be ignored: >iv. Never use the passive where you can use the active. Orwell himself routinely ignores it, even in the first sentence of the essay: >Most people who bother with the matter at all would admit that the English language is in a bad way, but it is generally assumed that we cannot by conscious action do anything about it. The second clause could be rewritten in active voice by cha…

> But Orwell's rule 4 should be ignored ... Orwell himself routinely ignores it, even in the first sentence of the essay

Orwell can answer you himself if you read just a little further:

> vi. Break any of these rules sooner than say anything outright barbarous.

Re: The revolt of the reader

#213

Post by jodrellblank »

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…

> "My revolt is against the cognitive stress of reading generated text."

I saw a comment on HN that that was roughly "re: ChatGPT, when I write one sentence and I get back three screens of lecture, I don't consider that a 'chat'".

I consider that comment often when prompting Claude and hoping for a two line response and getting an "it's important to note that ".

At some point it may as well be the teacher in a Charlie Brown cartoon: https://annotatedgilmoregirls.com/wp-content/uploads/2017/11...

audio version: https://www.youtube.com/watch?v=ss2hULhXf04

Re: The revolt of the reader

#215

Post by benmmurphy »

juliansimioni wrote: post #57
bcantrill wrote: post #29

Earlier quoted context omitted.

Right?! When I hit "That work was genuinely valuable" I literally hollered in exasperation.

For me it was “the results speak for themselves” and then simply a (large) number of automated tests run that never had human eyes. Yes, quantity famously has a quality all its own, but perhaps not where correctness checks for something this central is concerned.

I saw 'the results speak for themselves' but for me this article seemed to have less LLM-ese than some of the more recent obvious LLM prose posted to hackernews. As a reader I think its jarring because you just see a lot of articles purportedly written by different people using a very similar voice. I guess pre-LLM you might see this in a newspaper with very strong editorial oversight. So the phenomena is not completely new but it feels stranger when its not from a single source. It's also kind of sad to see a some people who have written a lot in the past about interesting technical topics in a way that was easy to read to give up their voice and outsource it to an LLM. But given this is basically free labour from the authors it feels a bit ungracious to complain.

Re: The revolt of the reader

#216

Post by Forgeties79 »

rcxdude wrote: post #26
Lerc wrote: post #13

How can you tell if people can accurately identify AI generated text? If a person reads AI generated text and does not notice, they by definition will not know about it. There have been numerous cases of people accessing human created content as being AI. There are instances where it seems relatively uncontroversial that it is AI generated, but without knowing both the amount of AI content people are exposed toand th…

I don't think this is about edge cases where someone has successfully disguised the writing to some degree: the current crop of LLMs have some pretty blatant (and frankly annoying) habits by default, ones that are hard to miss once you have read a decent amount of their output. If I had to describe them broadly, I would say they are a collection of habits which are common in certain kinds of persuasive and emotive wr…

> bombshell news article

That’s the aspect I’ve had a hard time articulating. Definitely the right comparison. It feels like some huge revelation has been had and it’s so consequential and it’s unbelievable that it’s happening right before your very eyes and wow aren’t you so insightful and pushing the boundaries of knowledge!?

That plus the “it’s not X, but why” nonsense makes it feel like some condescending parent is trying to lecture me but at least 30% of what they’re saying is probably made up.

Re: The revolt of the reader

#217

Post by esjeon »

grey-area wrote: post #180
esjeon wrote: post #120

Earlier quoted context omitted.

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...

Ah, I just read through it. That’s was a fun read.

> This is a parody, but not a very gross one. …

So, Orwell wrote the second sentence as a parody of the first sentence, using the modern English that he was criticizing in the essay.

> … in the middle the concrete illustrations – race, battle, bread – dissolve into the vague phrase ‘success or failure in competitive activities’. …

> … The whole tendency of modern prose is away from concreteness. …

> … The second contains not a single fresh, arresting phrase, and in spite of its 90 syllables it gives only a shortened version of the meaning contained in the first.

He tried to argue that the second one is worse, but, unfortunately, he successfully simulated one possible interpretation of the original. Sure, the parody has narrower meaning, but it is a valid subset of the original meaning, which is still very significant tbh. This justifies the reduction of “race, battle, bread” into “success or failure”, invalidating one of his points.

Also, the parody is not necessarily less concrete. It replaced poetic expressions in the original with words that are bloated, for sure, yet more concrete. It does have awkward expressions, but every word plays a role in the sentence. This basically conflicts with one of his criticisms in the essay — meaningless words.

Funnily enough, his another example — “some comfortable English professor defending Russian totalitarianism” — also fails to capture the nature of the modern English. He points out the “euphemism” towards the violence as an issue of style, but, no, that’s the whole purpose of it, and his example really just excel at it. Style-wise, again, the writing is very solid.

All in all, Orwell simply failed to properly simulate what he was trying to criticize. Good examples of “modern English” can be found in the earlier part of the essay, basically written by other people. Those examples do fit into Orwell’s criticisms.

Re: The revolt of the reader

#218

Post by knollimar »

OroPla wrote: post #166
masswerk wrote: post #98

Earlier quoted context omitted.

In contemporary YouTube-script wording: > The Ecclasiast looked under the sun, but there was something he didn't understand. Something that wasn't right. Something that was not as it was supposed to be. And here is what the Ecclesiast didn't understand. Here is what nobody understood. Not then. Not in the years that followed. Not now. It was not the swift who won the race. Not the strong who won the battle. Not the w…

I already notice LLM speech patterns in people that use them a whole lot. If you speak more than one language I recommend talking to LLMs in a language that you don't use when speaking to people.

The most frustrating one is when it does the papering over analysis and adding pushback to seem helpful. No, there shouldn't be a spot "where you pushback" unless it makes sense and responds to someone's concern!

Like with an LLM I would rewind the conversation. What do I do, shame them?

Re: The revolt of the reader

#219

Post by knollimar »

masswerk wrote: post #186
jbeninger wrote: post #169

Earlier quoted context omitted.

That's not a generator tell when used judiciously. It's a genuinely useful construction that's been poisoned by overgeneration.

That's the flaw in RLHF: constructs tagged as effective or sophisticated speech become templates, are increasingly used out of context (e.g., "not just A, not just B, but C" is usually meant to provide some synthesis and further the progress of the text) and suffer from significant overexposure. (And gone is the em-dash…)

I think the grating one is that it's constructed to sound effective when it shouldn't!

Good points should be rewarded confidence. I read so many not X it's Y where the distinction beteeen X and Y isn't relevant to the discussion!

Re: The revolt of the reader

#220

Post by knollimar »

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…

"a clear mental image from the very first word"

Nothing meaningful was said for 9 words.

Objective consideration of contemporary phenomena compels the conclusion that the words appearing here could be anything

Post reply on HN