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

Semantic ablation: Why AI writing is generic and boring

theregister.com

Post reply on HN
Print view View original

191–200 of 234 posts

Re: Semantic ablation: Why AI writing is generic and boring

#191

Post by johnnienaked »

barrkel wrote: post #3

This is a good statement of what I suspect many of us have found when rejecting the rewriting advice of AIs. The "pointiness" of prose gets worn away, until it doesn't say much. Everything is softened. The distinctiveness of the human voice is converted into blandness. The AI even says its preferred rephrasing is "polished" - a term which specifically means the jaggedness has been removed. But it's the jagged edges,…

Well said. In music, it's very similar. The jarring, often out of key tones are the ones that are the most memorable, the signatures that give a musical piece its uniqueness and sometimes even its emotional points. I don't think it's possible for AI to ever figure this out, because there's something about being human that is necessary to experiencing or even describing it. You cannot "algorithmize" the unspoken.

Re: Semantic ablation: Why AI writing is generic and boring

#192

Post by 8bitsrule »

yoyohello13 wrote: post #20
amelius wrote: post #7

Earlier quoted context omitted.

I'm sure this can be corrected by AI companies.

The question is… why? What is the actual human benefit (not monetary).

IME, in prose writing, arguing with LLM can help a newer writer to gather 'the facts' (to help with research) and 'the objections to the facts' (same result) to anticipate an initial approach to the material. This can save a lot of organizational time. After which, newer writer can more confidently approach topics in their own voice.

Re: Semantic ablation: Why AI writing is generic and boring

#193

Post by raincole »

tasty_freeze wrote: post #23

Bible Scholar and youtube guy Dan McClellan had an amazing "high entropy" phrase that slayed me a few days ago. https://youtu.be/605MhQdS7NE?si=IKMNuSU1c1uaVCDB&t=730 He ended a critical commentary by suggesting that the author he was responding to should think more critically about the topic rather than repeating falsehoods because "they set off the tuning fork in the loins of your own dogmatism." Yeah, AI could not…

> they set off the tuning fork in the loins of your own dogmatism

Sounds like word salad. Of course if you write like GPT-2 it would not sound like current models.

Re: Semantic ablation: Why AI writing is generic and boring

#194

Post by anon-3988 »

baxtr wrote: post #103
barrkel wrote: post #3

This is a good statement of what I suspect many of us have found when rejecting the rewriting advice of AIs. The "pointiness" of prose gets worn away, until it doesn't say much. Everything is softened. The distinctiveness of the human voice is converted into blandness. The AI even says its preferred rephrasing is "polished" - a term which specifically means the jaggedness has been removed. But it's the jagged edges,…

I think it’s essential to realize that AI is a tool for mainstream tasks like composing a standard email and not for the edges. The edges are where interesting stuff happens. The boring part can be made more efficient. I don’t need to type boring emails, people who can’t articulate well will be elevated. It’s the efficient popularization of the boring stuff. Not much else.

> The edges are where interesting stuff happens. The boring part can be made more efficient. I don’t need to type boring emails, people who can’t articulate well will be elevated.

I think that boring emails should not be written. What kind of boring emails do you NEED to be written, but not WANT to write? Those are exactly the kind of email that SHOULD NOT be passed through an LLM.

If you need to say yes/no. You don't want to take the whole email conversation and let LLM generate a story about why you said yes/no.

If you want to apply for a leave, just make it optimal "Hi , I want to take leave from Y to Z. Thanks". You don't want to create 2 pages of justification for why you want to take this leave to see your family and friends.

In fact, for every LLM output, I want to see the input instead. What did they have in mind? If I have the input, I can ask LLM to generate 1 million outputs if I really want to read an elaboration. The input is what matters.

If I have the input, I can always generate an output. If I have the output, I don't know what was the input (i.e. the original intention).

Re: Semantic ablation: Why AI writing is generic and boring

#196

Post by haffi112 »

lakhotiaharshit wrote: post #159

This article on AI writing being boring seems to be written by AI. The em dashes and the sentence structure, all seems to be AI output. Or have human started adopting this style too.

Oh the irony, I also felt that way when I started reading it. It borders on being hypocrisy given the topic of the article.

Re: Semantic ablation: Why AI writing is generic and boring

#197

Post by tpoacher »

dvt wrote: post #136
tpoacher wrote: post #134

The part about a change in entropy was interesting. Is there an easy way to get / compare the entropy of two passages? (e.g. to see if it has indeed dropped after gen ai manipulation). And could this be used to flag AI-gen text (or at least, boring, soulless sounding text)

A lot of times, this entropy decay is found in semantic or stylistic space, which would be hard to detect (you couldn't use, e.g., Shannon Entropy). You'd have to ask questions like "is this point uninteresting?" or "is this trope overused?"--bad (human) writers are often guilty of this too, so that's why AI can be hard to detect.

Yes, still though, it might be interesting to be able to measure this easily.

E.g. when asking an AI to rephrase or summarise, if the entropy drops you might take that as a sign that it has eroded the style beyond what you might be willing to tolerate.

I wonder if the author had a particular method / tool in mind, or if they were just speaking abstractly.

Re: Semantic ablation: Why AI writing is generic and boring

#198

Post by co_king_5 »

FooBarWidget wrote: post #150
co_king_5 wrote: post #36

Earlier quoted context omitted.

[dead]

So what even if that is true? You confirmed that it improved upon what he could manually produce, which is still a win. It doesn't always make sense to pay $20000 to a professional author to turn it into a masterpiece.

[dead]

Re: Semantic ablation: Why AI writing is generic and boring

#199

Post by zigzag312 »

datsci_est_2015 wrote: post #189
svara wrote: post #84

Earlier quoted context omitted.

I think that mostly depends on how good a writer you are. A lot of people aren't, and the AI legitimately writes better. As in, the prose is easier to understand, free of obvious errors or ambiguities. But then, the writing is also never great. I've tried a couple of times to get it to write in the style of a famous author, sometimes pasting in some example text to model the output on, but it never sounds right.

> I think that mostly depends on how good a writer you are. A lot of people aren't, and the AI legitimately writes better. Even poor writers write with character. My dad misspells every 4th word when he texts me, but it’s unmistakably his voice. Endearingly so. I would push back with passion that AI writes “legitimately” better, as it has no character except the smoothed mean of all internet voices. The millennial gr…

AI averages everything out, so there's no character left.

Similar thing happens when something is designed by a committee. Good for an average use, but not really great for anything specific.

Re: Semantic ablation: Why AI writing is generic and boring

#200

Post by cadamsdotcom »

If the “amount of semantic ablation” in a generated phrase/sentence/paragraph can be measured and compared, then a looped process (an agent) could be built that tries to decrease that..

It might come up with something original - I mean there has to be tons of interesting connections in the training data that no one’s seen before.

But maybe it’d just end up shouting at you.

Post reply on HN