this post was submitted on 19 Feb 2025
1237 points (99.8% liked)

Programmer Humor

20829 readers
2510 users here now

Welcome to Programmer Humor!

This is a place where you can post jokes, memes, humor, etc. related to programming!

For sharing awful code theres also Programming Horror.

Rules

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 94 points 1 week ago (20 children)

I remember when compression was popularized, like mp3 and jpg, people would run experiments where they would convert lossy to lossy to lossy to lossy over and over and then share the final image, which was this overcooked nightmare

I wonder if a similar dynamic applies to the scenario presented in the comic with AI summarization and expansion of topics. Start with a few bullet points have it expand that to a paragraph or so, have it summarize it back down to bullet points, repeat 4-5 times, then see how far off you get from the original point.

[–] [email protected] 51 points 1 week ago* (last edited 1 week ago) (10 children)

In my experience, LLMs aren't really that good at summarizing

It's more like they can "rewrite more concisely" which is a bit different

[–] [email protected] 3 points 1 week ago (1 children)

If it isn't accurate to the source material, it isn't concise.

LLMs are good at reducing word count.

[–] [email protected] 1 points 1 week ago

In case you haven't seen it, Tom7 created a delightful exploration of using an LLM to manipulate word counts.

load more comments (8 replies)
load more comments (17 replies)