1269

theFutureOfCommunication (lemmy.blahaj.zone)

submitted 2 months ago by cm0002@lemmy.world to c/programmer_humor@programming.dev

73 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] ragebutt@lemmy.dbzer0.com 99 points 2 months ago

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.

[-] Kache@lemm.ee 53 points 2 months ago* (last edited 2 months ago)

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

[-] merc@sh.itjust.works 37 points 2 months ago

Summarizing requires understanding what's important, and LLMs don't "understand" anything.

They can reduce word counts, and they have some statistical models that can tell them which words are fillers. But, the hilarious state of Apple Intelligence shows how frequently that breaks.

[-] Droggelbecher@lemmy.world 23 points 2 months ago

I used to play this game with Google translate when it was newish

[-] toynbee@lemmy.world 17 points 2 months ago

There is, or maybe was, a YouTube channel that would run well known song lyrics through various layers of translation, then attempt to sing the result to the tune of the original.

[-] Whelks_chance@lemmy.world 9 points 2 months ago

Gradually watermelon... I like shapes.

Twisted translations

[-] toynbee@lemmy.world 5 points 2 months ago

Sounds about right to me.

[-] Viking_Hippie@lemmy.dbzer0.com 6 points 2 months ago

🎵Once you know which one, you are acidic, to win!🎵

[-] sp3tr4l@lemmy.zip 9 points 2 months ago

translation party!

Throw Japanese into English into Japanese into English ad nauseum, untill an 'equilibrium' statement is reached.

... Which was quite often nowhere near the original statement, in either language... but at least the translation algorithm agreed with itself.

[-] spankmonkey@lemmy.world 4 points 2 months ago

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

LLMs are good at reducing word count.

[-] eRac@lemmings.world 1 points 2 months ago

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

[-] baines@lemmy.cafe 2 points 2 months ago

you mean hallucinate

[-] AmidFuror@fedia.io 49 points 2 months ago

A couple decades ago, novelty and souvenir shops would sell stuffed parrots which would electronically record a brief clip of what they heard and then repeat it back to you.

If you said "Hello" to a parrot and then set it down next to another one, it took only a couple of iterations between the parrots to turn it into high pitched squealing.

[-] Kusimulkku@lemm.ee 2 points 2 months ago

Reminds me of this classic video https://www.youtube.com/watch?v=t-7mQhSZRgM

[-] icosahedron@ttrpg.network 11 points 2 months ago* (last edited 2 months ago)

i was curious so i tried it with chatgpt. here are the chat links:

overall it didn't seem too bad. it sort of started focusing on the ecological and astrobiological side of the same topic but didn't completely drift. to be honest, i think it would have done a lot worse if i made the prompt less specific. if it was just "summarize this text" and "expand on these points" i think chatgpt would get very distracted

[-] ragebutt@lemmy.dbzer0.com 4 points 2 months ago

Interesting. I also wonder how it would fare across different models (eg user a uses chatgpt, user b uses gemini, user c uses deepseek, etc) as that may mimic real world use (such as what’s depicted in the comic) more closely