I summarize HN threads, blog posts, YT videos, etc. to see if the content is worth my time. So far I've used Perplexity extension.

As a heavy LLM user, professionally and personally, I use "summarize this" a lot - I find that most content in the world is low signal-to-noise and a lot of the time the salient / useful information is hidden within unnecessary layers.

The only time I didn't think summaries are useful is with creative fiction or pure entertainment content.

Recipes.

"Summarize it. Keep only instructions and ingredients (more prompt about how to format instructions, what units to use, how to order instructions) and start with one sentence that describes the dish and it's origin"

Which is a terrible waste, really. Many recipes are blown up to make them copyrightable. Often done with AI. And then I use AI to remove all that again.

> Many recipes are blown up to make them copyrightable.

To attempt to make them copyrightable at least. My understanding is that fundamental recipes themselves as sequences of steps and ingredients are never copyrightable in the US. From having sat around a lot of recipe bloggers though it sounds like the main reason they do the long essays is to try and improve search ranking.

Recipe sites always have a print button which gives you just the recipe. If I end up on one of those sites I instantly hit Ctrl+F "print" to get it.

The Firefox Addon RecipeCleaner can also do that for you

Try to look at the recipe page without adblock. You will see ads every couple sentences. Longer article more ads.

Imagine a horrific world where most articles are 5 pages of LLM generated fluff from a 10 bullet point sentences prompt. I know, truly a nightmare world. But in this world, wouldn't it be great to just collapse all those articles down to their original prompt? A sort of reverse-fluffing. So maybe I can't convince you of how great it is in our world, but hopefully at least in this hypothetical world it makes sense.

I’ve got one. When estimating tasks, there’s a particular blog article I like to reference [0] and I used an LLM to summarize it into a set of project instructions.

Did it read the summary? Nope, I already know the material and have been using it for years. But it was a great way to communicate the key points to the model as part of project instructions.

[0]: https://jacobian.org/2021/may/25/my-estimation-technique/

Ah OK.

So in this case, this was not you trying to ingest a condensed version of the info, but rather transforming it to build a prompt (under the assumption that shorter instructions would perform better than the full article).

Makes sense

The text summary for group chats provides a lot more information at a glance than “21 new messages”

Corporate org level announcement mails

So Management went to ChatGPT and asked, "can you write a launch email about $event_x " and you then go there to ask, "what did management want to say in this email about $event_x"?

How likely is it that the output summary is mostly made of stuff that the LLM made up in the first expansion process? (eg, you're getting summarized noise if the original signal - the prompt - was much shorter than the email)

Unnecessary long-form news articles that bury the lede.

I've been using it on my own written docs to see what my co-workers inevitably see

Wow, that is both hilarious, depressing, and something that I think I'll start doing now. Thanks

I use it on my own docs to remove extraneous details. I often write too many words in early drafts and LLMs summarize my writing faster than I can (although I don't know if they do it better than I would/could).

Then the next version of my doc becomes the summarization, and I only flesh out details where the summarization went too far and removed critical details.

Long articles that I don't have time to read fully and that contain a lot of words serving only as placeholders, without changing the main message or information.

Yeah we already have a perfectly serviceable way to extract the meat from an article and avoid the filler (i.e. don't click just read the headline)

> (i.e. don't click just read the headline)

And the HN comments!

I don't use it to summarize, but I like to ask about the key takeaways for long-form content. E.g., "what did he say that was noteworthy or new about X [in this long interview I don't time to read right now]"

Any recipe page on the Web is unreadable without summarization cause they are made for seo.

New York Times (and other magazines) articles. "On a quiet Sunday morning..." - No, I don't care about it, just tell me the damn thing (which usually can be done in 4-5 sentences).