Hacker News Reader

Comment by trollbridge | Hacker News Reader

Well, you can use LLMs to parse LLM-generated slop. They make nice summaries. I have taken this approach to people who send me obviously generated LLM text; I simply run it through an LLM, paste the summary, and ask them "Is this an accurate summary?" and then I ask the for their original prompt.

View on HN

This puts the LLM providers in a great position of:

    <prompt text> -> [PROVIDER] -> <lots of output text> -> [PROVIDER] -> <prompt text, mangled>

They're getting paid to encode some inane prompt into paragraphs of text, and then they're getting paid again to summarize that back into something with even less value than the original prompt. And they're making money hand over fist because people are happier to play that game rather than just pushing back on the jerks sending them pages of generated garbage in the first place.

I would agree with you, except right now the walls of text come from people using the free or very cheap versions of ChatGPT, et al. So there's not even anyone making money off of it.

Ah yes, take my single sentence, blow it up to 3 paragraphs with LLMs, and then the person reading it can have an LLM summarize it in a single sentence.

What the fuck are we even doing anymore?

I wonder if that even works. Kinda like when kids play telephone I think it’s unlikely the input and output sentences actually match.

The thing is, eventually these products will be more integrated into business workflows and have access to all the context, so the three paragraph expansion probably will be a significant improvement upon the original input.

And either that person won't be employed anymore, of the thing they were asking for in the first place will be automated for them.

I've already got my agent building a dossier for everyone we interact with. I haven't started training it on their writing style so I can mirror back to them... yet.

As these products improve, one person sending the output and not the prompt will remain useless. The prompt captures the intent and level of real consideration of the person sending it, the receiver can augment that with additional information if they want to.

That's like saying I should just send the English teacher a description of what my essay will be about, instead of actually writing it.

It seems like no one responding to this understands scoped context retrieval.

Professional communication has a completely different goal than a student essay, and it's weird you conflate the two. A student paper is useless as an artifact, the actual value is for the student to learn how to write the paper. If a coworker sends me a long email for me to read it should provide some actual value.

I'm arguing against people who essentially say that running the LLM is useless; just send the prompt.. Obviously that is true if the person does zero additional value add, but then that person probably sucked as a colleague before LLMs anyway. When you use an LLM agent correctly you are adding value beyond just the prompt, and those three additional paragraphs won't just be extra noise. Especially if the agent is automatically fed your personal context.

An essay states a hypothesis and then uses first and second party sources to validate it. I'm not conflating anything, it's just a good abstract example of the type of knowledge synthesis work, which is why we make kids do them.

A business strategy proposal is nothing more than a specific type of essay where the research sources are internal research results, market trend analysis, etc.

A technical design doc is an essay about the best way to implement a feature.

An "executive summary" is just an abstract, and the MBR puts the latest research citations and raw results in bullet points.

> When you use an LLM agent correctly you are adding value beyond just the prompt, and those three additional paragraphs won't just be extra noise.

So send me the prompt and the three extra paragraphs that you wrote. The improved LLM will generate the additional context for me if I need it. But heck, maybe I wrote that context myself or have read it many times and don't need it parroted back to me.

Currently they are inferior.

> I've already got my agent building a dossier for everyone we interact with. I haven't started training it on their writing style so I can mirror back to them... yet.

have you asked these people how they feel about this? have you asked them for permission, for their consent to do this with their communications to you?

what you’re doing sounds incredibly creepy. like, meta/facebook kinda of creepy. granted, it’s at a more limited scale, but it’s still creepy af dude.

fwiw, if i was your colleague and you asked me how i felt about you doing this with me, i’d be seeing about getting HR involved.

Well, implicit in the TOS of things like Gmail, etc. is already permission to do this.

does that make it morally okay to do with your colleagues?

like, jfc, these are fucking people were talking about building “dossiers” of. people the person works with where a degree of trust and bonding is necessary. people they probably spend at least a quarter of their waking hours interacting with.

and your defence for it is “well, google does it”.

the best engineers know what not to build. they don’t build every single thing under the sun because they can.

also, don’t you have to explicitly agree to google’s terms for that stuff to use their services?

That’s not how the real world works. You will be kicked out of the workplace and rightly so.

Um, I absolutely expect my colleagues to update their internal model of me every time we communicate, to a greater or lesser degree depending on how much that communication deviates from their expectations, or how much new information it contains. In fact, that is essentially the purpose of communication.

Do you think you are not constantly being "influenced" to do what people want from you?

What do think happens during a peer review or promotion decision?

What do you think the pile of data in SharePoint / GDrive represents?

You think HR will care about someone taking prolific detailed notes at work?

I did phrase my comment in a glib way to draw out this type of reaction. But this type of stuff is what "intelligence augmentation" will include, and the corporate panopticon is already alive and well anyway.

their mental model. the human being’s mental model. the one in our private head. not some model on a corporate server, some secret “dossier” on every interaction you’ve ever had with them. you’re basically creating your own black book / surveillance tool on everyone you interact with dude.

just because the corporations do this to us doesn’t make it okay to do it to each other. just because your employer does it doesn’t mean it’s okay to do to your co-workers. like, there has to be a degree of trust between colleagues dude.

compiling a record of every single thing anyone has ever said to you, an individual human being who is not a corporation or a machine, all for the purposes of “it makes my emails better” is just plain fucking creepy.

i think you might need some time away from the screen. seriously.

> i did phrase my comment in a glib way to draw out this type of reaction.

maybe, just maybe, it would be a good idea to take a bit of time to seriously think about why being glib about this super creepy thing you’re doing is not a good thing.

bit of self-reflection. the thing us humans are supposedly still capable of doing and the machines are not.

Really makes you wonder about freewill and information determinism

This is a pretty gross privacy violation but it's also just... So depressing.

My employer already records every scrap of communications, I'm running everything on corporate infrastructure, and they sent the information to me.

Giving the AI knowledge of the org chart, who works on what, how they prefer to communicate, what their goals/biases are, is no different than what every ape implicitly collects in their own head.

Oh I know. In the past month I’ve moved several thousand dollars in spending away from companies that turned their support into a useless understaffed AI program.

The disease has spread to six figure enterprise contracts hallucinating about their own APIs.

He's describing a 4 step process:

1) >I simply run it through an LLM,

2) >paste the summary,

3) >and ask them "Is this an accurate summary?"

4) >and then I ask the for their original prompt.

Agreed that just step 1 or step 1 and 2 would be depressingly pointless, but step 3 and 4 make this the equivalent of sending someone a let-me-google-that-for-you kind of link, does it not?

Caught out like this I imagine many people will kind of get the fact that you'd rather have their direct inputs..

(Or just get mad at you, but that's fair I guess)

Worse still, the person that is the most egregious about doing this seems to appreciate it and responds with "Yes, that's right!" and just ignores (or has no idea what I'm talking about) when I ask for the original prompt.

I simply ask for a positive affirmation of the summary so that I can act on that, instead of other things.

We're so close to realizing the answer was with us the entire time.

midwit meme template

guy on left: katie u want meet 3pm discuss project

midwit: Hi Katie, I hope this message finds you well and that your week has been off to a productive start. I wanted to reach out and proactively touch base regarding an opportunity to align on some of the ongoing project-related workstream...

guy on right: katie u want meet 3pm discuss project

LLMs are great at decompression [1]

[1] https://jabde.com/2026/02/02/utilizing-llms-as-a-data-decomp...

Nice article! I wrote something similar this year too after seeing the 5-bullet-points of information stretched out with AI homologous slop too many times.

https://www.vaines.org/posts/2026-01-26-jpeg-compression-for...

Might as well donate money to the AI companies at this point.

But now even this is just producing more information and requires more work both of you and of the original sender.

> and then I ask the for their original prompt.

Original prompt: "Please rewrite this information in a nice format for my insufferable asshole colleague".

Telephone game

Reply on news.ycombinator.com