Hacker Newsnew | past | comments | ask | show | jobs | submit | AstroBen's commentslogin

Just reading that plan would take weeks or months

You don't start with 100k lines, you work in batches that are digestible. You read it once, then move on. The lines add up pretty quickly considering how fast Claude works. If you think about the difference in how many characters it takes to describe what code is doing in English, it's pretty reasonable.

100,000 lines is approx. one million words. The average person reads at 250wpm. The entire thing would take 66 hours just to read, assuming you were approaching it like a fiction book, not thinking anything over

I've seen this too. What's confusing is they don't seem to be accomplishing anything? They're not pushing products

What's the point? To prime the account for later?


"can the bot army push average opinion x% in this innocuous topic?" it could very easily be a/b testing a propaganda system.

I wonder if it's due to diet. Endurance athletes love their simple carbs, highly processed gels. I've seen plenty of cyclists taking gummy bears on rides for fuel, or a concoction that is effectively sugar water to drink

The study referenced is really light on details and they don't say if they controlled for that


I was thinking the same thing.

Simple sugars and highly processed foods tends to affect the gut microbiome.

I guess "more ressearch is needed".


I wonder why fiber is never brough up with this. Only ~5% of people get enough fiber and it lowers your risk a lot

Fiber is so inconvenient to get in adequate quantity. We cook all our meals using tons of vegetables and none of it has much fiber if I remember. Occasionally I’ll try to start eating oatmeal but get burned out after a week or two.

My breakfast: 80g oats, 2tbsp chia seeds, 1tbsp ground flax, a shitload of frozen berries, 50g of mixed nuts (walnuts, almonds, whatever), raisins or other dried fruit

Delicious and has more than the recommended fiber in one meal. I didn't like oats much until I learnt how to make them taste good


This is close to a recipe suggestion on Bob’s Red Mill Muesli.

I would assemble it the night before, so that the berry juice moistened the oats.

Cardamom or cinnamon, honey, or plain yogurt can be added.


Sounds good how is this prepared?

How do you make them taste good? I need to put sugar on oatmeal... Lol

So put sugar.

I eat a lot of fibrous frankenfoods and I’m not sure if the net effect is positive, but I think it helps my bowel movements…

It’s covered in the risk factors section at the end.

Ah, you're right.

I actually looked it up after I made that comment and it looks to be a 10% reduction in relative risk per 10g extra fiber consumed

Considering Americans as an example only get 10-15g per day, and it's perfectly possible to get 60g.. that could have a huge impact


You can buy Psyllium husks by the pound as well.

There are apparently cases of psyllium leading to weird allergic reactions. IIRC this is frequently reported in caretakers who prepare psyllium for eldery patients, presumably because they end up inhaling some of the stuff?

TUIs have gotten so good lately. I love the design on this

Here's my definition of good writing: it's efficient and communicates precisely what you want to convey in an easy to understand way

AI is almost the exact opposite. It's verbose fluff that's only superficially structured well. It's worse than average

(waiting for someone to reply that I can tell the AI to be concise and meaningful)


Here's AI responding to you:

"You're describing the default output, and you're right — it's bad. But that's like judging a programming language by its tutorial examples.

The actual skill is in the prompting, editing, and knowing when to throw the output away entirely. I use LLMs daily for technical writing and the first draft is almost never the final product. It's a starting point I can reshape faster than staring at a blank page.

The real problem isn't that AI can't produce concise, precise writing — it's that most people accept the first completion and hit send. That's a user problem, not a tool problem."


I don't know if this happens to anyone else but on reading LLM-generated text I did not prompt, my eyes do incredibly quick saccades from start to middle to end in always around <1-2s no matter the length of the text.

It's entirely involuntary, I am just unable to care. It's almost always justified because the text in question is always painfully bloated, and repetitive.

The LLM-text you posted could have been (given I didn't read it carefully):

"Skill issue. Iterate on the output, never accept what you receive on the first pass"

Instead we get the standard:

- Agree with the user

- Lackluster simile

- Actual content

- Not X, Y. X, not Y.


> It's entirely involuntary, I am just unable to care

Me too. I don't know about the eye movements, but there are probably dozens of us being unable to focus on a LLM-text: https://news.ycombinator.com/item?id=46630931


This response provides the recommended daily allowance of irony.

> what was interesting about a "Show HN" post was that someone had the technical competence to put something together

Wouldn't the masses of Show HN posts that have gotten no interest pre-AI refute that?


This type of cadence.

You know the one.

Choppy. Fast. Saying nothing at all.

It's not just boring and disjointed. It's full-on slop via human-adjacent mimicry.

Let’s get very clear, very grounded, and very unsentimental for a moment.

The contrast to good writing is brutal, and not in a poetic way. In a teeth-on-edge, stomach-dropping way. The dissonance is violent.

Here's the raw truth:

It’s not wisdom. It’s not professional. It’s not even particularly original.

You are very right to be angry. Brands picking soulless drivel over real human creatives.

And now we finish with a pseudo-deep confirmation of your bias.

---

Before long everyone will be used to it and it'll evoke the same eugh response

Sometimes standing out or wuality writing doesn't actually matter. Let AI do that part


Only thing missing is, “The raw truth?” instead of, “ Here's the raw truth:”.

the LinkedIn register of English

I don't really remember Claude 3.5 doing this, but it seems increasingly worse, with 4.6 being so bad I don't like using it for brainstorming. My shitty idea isn't "genuinely elegant".

Why would anyone get sick of it if people have been happily doing it to each other for so many years prior?

Does the fact that a machine can ape it so easily somehow reveal its vacuousness in a way that wasn't obvious already?

I keep hearing people with job titles like "SEO growth hacker" saying it's depressing that AI can do their jobs better than they can.

Really? That's the depressing part?


No worse than "junior developer" assuming they were looking to move on from it

Writing SEO content for random sites was of course the lowest skilled writing job. Ideally they'd have higher aspirations than that though.

Maybe those people didn't even want to be writers. They just wanted an easy job.


This is what I don't grok...

Your sample sounds exactly like an LLM. (If you wrote it yourself, kudos.)

But, it needn't sound like this. For example, I can have Opus rewrite that block of text into something far more elegant (see below).

It's like everyone has a new electric guitar with the cheapo included pedal, and everyone is complaining that their instruments all sound the same. Well, no shit. Get rid of the freebie cheapo pedal and explore some of the more sophisticated sounds the instrument can make.

----

There is a particular cadence that has become unmistakable: clipped sentences, stacked like bricks without mortar, each one arriving with the false authority of an aphorism while carrying none of the weight. It is not merely tedious or disjointed; it is something closer to uncanny, a fluency that mimics the shape of human thought without ever inhabiting it.

Set this against writing that breathes, prose with genuine rhythm, with the courage to sustain a sentence long enough to discover something unexpected within it, and the difference is not subtle. It is the difference between a voice and an echo, between a face and a mask that almost passes for one.

What masquerades as wisdom here is really only pattern. What presents itself as professionalism is only smoothness. And what feels, for a fleeting moment, like originality is simply the recombination of familiar gestures, performed with enough confidence to delay recognition of their emptiness.

The frustration this provokes is earned. There is something genuinely dispiriting about watching institutions reach for the synthetic when the real thing, imperfect, particular, alive, remains within arm's length. That so many have made this choice is not a reflection on the craft of writing. It is a reflection on the poverty of attention being paid to it.

And if all of this sounds like it arrives at a convenient conclusion, one that merely flatters the reader's existing suspicion, well, perhaps that too is worth sitting with a moment longer than is comfortable.

----

(prompt used: I want you to revise [pasted in your text], making it elegant and flowing with a mature literary-style. The point of this exercise is to demonstrate how this sample text -- held up as an example of the stilted LLM style -- can easily be made into something more beautiful with a creative prompt. Avoid gramatical constructions that call for m-dashes.)


>It is not merely tedious or disjointed; it is something closer to uncanny, a fluency that mimics the shape of human thought without ever inhabiting it.

It still can't help itself from doing "it's not X it's Y". Changing the em-dash to a semi-colon is just lipstick


Yep. But that prompt I used was just a quirky. You can explicitly force it to avoid THAT structure as well. Just do what the smart ?ie, devious) middle-schoolers do: find a list of all the tell-tale ‘marks’ of AI content, and explicitly include them as prohibitions in your prompt… it’s the most basic work-around to the ‘AI spotters’ the teacher uses for grading your essay. (And, of course, be sure to include an instruction to include a grammatical or spelling error every few sentences for added realism.)

It's less obvious but it has the same problems. So many dramatic words to say so little and so many AI tics.

You're right, a lot of the style can be changed from its default. I don't think you can get rid of the soulless aspect though - the lack of underlying relatable consistency.

Especially once you go past a page or two.

When you get to the actual content so much of it just doesn't make sense past a superficial glance

Soulless drivel is very accurate


well done. :)

and at the same time the chop becomes long-form slop, stretching out a little seed of a human prompt into a sea of inane prose.


Of course people will buy software.. but the 80% margins we had of yesteryear won't be there

The result of the barrier to entry being erased is that prices will also be driven to 0 as products are commoditized

It's hardly worth going into a market when you're 1 of 1000 and profit margins are at 3%

Any creativity you add, new spin you put on it, new features, innovation.. all that has negligible cost to copy

I don't think we're quite there yet, but this is where it's quickly heading


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: