Hacker News Reader

Comment by whycome | Hacker News Reader

What already happens: - People give an LLM a bulleted list of points that they want expanded into a professional sounding document. - The receiver doesn't wanna read all that. They put the full document into an LLM and ask it to summarize it into succinct bullet points.

View on HN

We've invented the opposite of lossless compression

A broken telephone.

TAM: $50T

It's been a huge boon to hardware vendors.

Lossy expansion or bloat?

Depends on if you are buying tokens or being paid for tokens

Students where doing that for the ages when they have to answer questions like. "Answer the following question in not less than 4 pages"...

In that case it's supposed show that the student can write four pages and not just about transferring information.

Seven bullet points squeezed into five pages of text

I first noticed this a year ago when I read a gmail AI summary, then glanced at the main text and saw it was AI generated. I feel like there's good fodder in there for a dystopian sci-fi story about a future where nobody communicates directly with one another, it's all AIs translating, but the AIs slowly start to drift.

Agreed re: the sci-fi story / trope.

I feel like a lot of this is a problem when someone technical is attempting to communicate a complicated technical subject to a less-technical audience.

I can only dumb a thing down so much before the description is useless (when you zoom out too much you lose the details). Even technical people who could understand it but are lazy / "in a hurry" use the summary, without thinking about what detail they are losing.

Even more infuriating is when they then reply to my email, having only read the AI summary, and ask a question that was already answered by my message.

This is the exact same thing that happened pre-AI, with the added step of wasting energy/resources on the AI summary in the middle.

E. M. Forster wrote that story in 1909.

https://web.cs.ucdavis.edu/~rogaway/classes/188/materials/th...

Adrian Tchaikovsky has a good take on it as well, Human Resources.

>but the AIs slowly start to drift.

It's essentially the tower of babel. Each person will devolve to speak their own internal language only they understand. Each language will need to be encoded down to its meaning to be reinterpreted. None of us will know if the transformers are accurately decoding, or if the other person is accurately interpreting the decoding (which is arguably already a feature of human language without the computers in-between.)

It was in a gmail promotional video years ago already. Person A would use AI to turn their summary into email and person B would ask the AI to go back to the summary.

They knew it was going to be like that from the beginning.

I’ve been saying the same thing. I’m not saying all, but a significant amount of comms could be bullet points to the benefit of both sender and receiver.

Axios built a hefty business off this simple idea

This is exactly what I want: To communicate with me, have your LLM expand your message to include relevant parts of _your_ context, then I will have my LLM summarize it as briefly as possible with respect to _my_ context.

Just ask them for their prompt, and then put that in your own LLM with your own context. Why do you need their LLM's fluff?

Reply on news.ycombinator.com