this post was submitted on 15 Jul 2023
501 points (95.8% liked)

Technology

59106 readers
3421 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
 

ChatGPT use declines as users complain about ‘dumber’ answers, and the reason might be AI’s biggest threat for the future::AI for the smart guy?

top 50 comments
sorted by: hot top controversial new old
[–] ragnar_ok@discuss.tchncs.de 140 points 1 year ago* (last edited 1 year ago) (15 children)

The free version of ChatGPT DEFINITELY is dumber than it was even a couple of months ago. Used to be able to get decent, useful code reviews out of it, now it barely knows how to write a nested loop anymore.

It’s storytelling capabilities fell off a cliff too, the drive towards safely sanitized unoffensive-at-all-times content it can output has rendered every story, choose-your-own-adventure or collaborative role playing game sterile, empty expressions of black and white stories with no nuance allowed where saintly goodness is the only choice possible

In my own experience, chatGPT has been massively nerfed for the use cases I used it for

[–] Pixlbabble@lemmy.world 38 points 1 year ago (1 children)

I tried a naughtybot for some steamy chat for the first time yesterday. I ended up in fight with the bitch.

load more comments (1 replies)
[–] Kerfuffle@sh.itjust.works 16 points 1 year ago (1 children)

65B LLaMA models can actually do a pretty good job of writing. Here's two examples with Guanaco 65B (bold part is my prompt):

tags: fairy tale, animals, dog, wolf, fox, death, humor, dark storyline, violence, loss

Animals in a forest setting investigate a series of gruesome murders that recently occured. Written in the style of classics like Animal Farm and Watership Down, the writing is vivid and very descriptive. The dialog is thoughtful and often quite witty. It's clear the author really understands animal behavior and has done their research well!

---

Chapter 1: An Unfortunate Discovery

A fox by species, a detective by trade, you'll only have reason to know my name if the worst has come to pass. It's nearly winter and a bitter wind drives stinging sleet into my face, but it's still not as chilling as the scene before me now...

I was summoned here by an urgent message from a panicked hedgehog. She told me she found her friend lying dead on his doorstep with his throat ripped out - black fur matted with blood. I rushed over immediately and saw for myself what had happened. He looked so peaceful despite being cut down in his prime - a young wolf just starting doing well for himself - taken too soon. His home nearby showed no signs of struggle or forced entry. Whoever did this must have caught him off guard somehow. I didn't hear any howling either. That would have been easy enough to miss though since he lived alone deep in these woods where few creatures tread. I made sure to secure the crime scene and look around carefully without disturbing anything more than necessary until other investigators arrived. They should be here soon. We can't afford to lose evidence in cases like this. Times are already hard enough as it is...

As I waited and pondered who might have committed such a horrible act, something felt wrong about all this. Surely a predator like me could smell another predator's scent? But there were none that stood out among the melange of odors lingering here. How strange...

Soon after, several others joined me including some friends of mine. A stoic bear named Growler, grumpy badger called Grumpus, and a kindly old raccoon who goes by "Doc" due to his extensive knowledge of medicinal plants and wildlife biology. Together we began our investigation proper by gathering clues and questioning nearby witnesses while trying to minimize contamination through contact with them (we took care to put up caution tape first). Unfortunately, they hadn't seen much useful apart from occasional glimpses of movement deeper in the undergrowth. Still, we decided to check those areas next along with searching the surrounding woodlands thoroughly for any additional victims. And find one we did, although sadly she suffered the same fate as poor George. Another young wolf lay beside a stream, body cold and stiffening. Someone snapped her neck cleanly like a twig. This couldn't be coincidence surely? Not two deaths in quick succession like this.


before me or what I must relay when I return home. My mind races with questions as I survey this brutal crime scene; who could do such a thing? Why was no one there to stop them? And how many more victims lie undiscovered further out in these woods? A lone paw print leads away from where a rabbit family once happily resided, now reduced to bloody scraps scattered among splintered twigs and torn fur. This isn't just some random predator attack, something far more sinister is at play here...

I turn back toward town, determined to find answers. As I trudge through the snow, each step feels heavier than the last. How will I break the news to those closest to them? What words can possibly bring comfort after so much senseless suffering? I shake my head, trying to focus on the task at hand. There are others depending on me right now, they need someone strong and steady to guide them through this darkness. I won't let them down.

The first person I see upon entering town is old man Badger, his white whiskers blown about by the gusting wind. He looks up at me expectantly, "Well Fox, did you find anything?" His voice quavers slightly, betraying his concern for the missing families.

"I'm afraid I have bad news," I say somberly, "there were signs of a struggle near the burrow entrance, but no survivors."

Badger sighs heavily, "Dear me, this is worse than we feared. We must alert the council immediately!"

We hurry over to the meeting hall, a large hollow tree that serves as our central gathering place. Inside, several other animals are already waiting anxiously for word of their loved ones. They look up hopefully as we enter, then quickly realize the grim tidings we bear. A collective groan fills the room, followed by muffled sobs and whispered prayers.

Mayor Bear calls for order, her deep voice cutting through the din. She motions for us to join her at the front of the room, "Please tell us everything you saw, Fox. Every detail may be important."

[–] Calimhero@lemmy.world 34 points 1 year ago (2 children)

Writer here. Very sorry to contradict you, but this is absolute shit. It looks good on the surface, but that's all.

[–] spark947@lemm.ee 16 points 1 year ago* (last edited 1 year ago) (1 children)

Yeah, while it's cool that a computer can make a story, I have yet to see one that you would think was written by a human and would want to read.

[–] bitcrafter@lemmy.sdf.org 9 points 1 year ago

I don't know, this story is very reminiscent of the kind of thing my elementary school age cousin writes, but with a greater mastery of vocabulary and grammar. It's not in any way great, bit it's charming in it's own way when held against that (low) standard.

[–] Kerfuffle@sh.itjust.works 15 points 1 year ago (5 children)

Very sorry to contradict you, but this is absolute shit.

To be clear, I'm talking in relative terms. Would you argue that ChatGPT did a massively better job and didn't write "absolute shit"?

It looks good on the surface, but that’s all.

From some of the stuff I've seen published, that might just be enough for certain people. I could even be that "certain people" from time to time, sometimes just the right theme, setting and some time to fill is sufficient.

load more comments (5 replies)
[–] mememuseum@lemmy.world 7 points 1 year ago (3 children)

Do you know of any good alternatives for role playing? I used it a while back to flesh out some NPCs and location for a DnD game I was planning on running but if it's gotten noticeably worse I'd like to try something else.

load more comments (3 replies)
load more comments (12 replies)
[–] Strangle@lemmy.world 72 points 1 year ago (4 children)

Back in my day, we used to call ‘prompt engineering’ ‘asking a question’.

[–] unreachable@lemmy.my.id 43 points 1 year ago (5 children)

back in my day, we call it "google fu"

[–] nottheengineer@feddit.de 38 points 1 year ago (2 children)

And then we had to actively unlearn that google fu because google no longer works with keywords, but rather has an NLP pipeline that expects a question.

[–] LordXenu@lemmy.world 25 points 1 year ago (1 children)

So that’s why I can’t find shit. I always just use keywords, asking a whole question seems almost wasteful.

[–] Sylver@lemmy.world 18 points 1 year ago (2 children)

Wow, no wonder most of the old search commands don’t even feel like they work…

[–] clearleaf@lemmy.world 26 points 1 year ago (1 children)

The last straw in utterly ruining it was when they removed using quotes to get exact matches. That was the only way to cut through the garbage. Now the only use for google search is searching within specific websites that never bothered to make their own decent search function.

load more comments (1 replies)
[–] LordXenu@lemmy.world 9 points 1 year ago

Fucking right?!

It adds this weird abstract where the search keywords the question you ask but that requires you to ask the right question. Sometimes I just need the page that has the most mentions of a specific word or phrase.

load more comments (1 replies)
load more comments (4 replies)
[–] CosmoNova@lemmy.world 13 points 1 year ago (2 children)

They got to have a special termonology because what they do is oh so special. Some AI users act like they're Louise Banks from the movie Arrival cracking the code to an alien language or something. And I don't think it's far fetched to assume they're often from the same breed who had NFT monkeys as their twitter pfp about 18 months ago.

load more comments (2 replies)
load more comments (2 replies)
[–] unhook2048@lemmy.world 36 points 1 year ago (1 children)

It's getting worse based on the feedback unfortunately, the need for safety and lack of meaningful deliberation towards how AI companies should operate and what should and should not be done has led Sam and co to be indesicive towards doing anything. Alongside the "morality" of the thing being hyjacked has lead to other AI's performing better... lead by x employees of OpenAI, with actual bound morals and not inherently relying on user input to train future models, this will be the path forward, this will lead to safe and controlled integration.

I guess at the core of this, we are afraid of ourselves. We are afraid that the worste of humanity outpaces the better parts, that the inputs and training aren't altruistic but are more pointedly "bad" or "wrong", and thus leading to "harmful", whether through misinformation, lies, or fabrications.

I hope we find a way to do better. I'm still excited for the future of AI, I mean crap, I'm closer to having a family doctor that's a robot then I am to a real human doctor.

[–] asparagus9001@lemmy.world 14 points 1 year ago

I guess at the core of this, we are afraid of ourselves. We are afraid that the worste of humanity outpaces the better parts, that the inputs and training aren’t altruistic but are more pointedly “bad” or “wrong”, and thus leading to “harmful”, whether through misinformation, lies, or fabrications.

Is there any reason not to be afraid? I think you could say that Tay was essentially the same idea a few years back and it took like 48 hours loose on the internet for it to spout literal Nazi (1930s-40s German NSDAP) rhetoric. Besides that being a PR disaster - if "AI" is only getting stronger and more integrated into human life and society, that can be pretty problematic.

[–] fidodo@lemm.ee 34 points 1 year ago

AI cannibalism simply isn't a thing yet. It definitely will be and good models will need to spend a lot of time and money sourcing good training data, but the models are not up to date enough to be contaminated yet.

I'm very confident the degradation has come from them trying to scale up. Generative AI is the most expensive thing on the cloud you can provide, and not only are they trying to make it faster, they're trying to roll it out for way more consumption. Major optimizations will require an algorithmic breakthrough so in the meanwhile all they can really do is find which corners they can cut that are less bad.

[–] dulce_3t_decorum_3st@lemmy.world 27 points 1 year ago (7 children)

Nonsense. Less people are using it because there are viable alternatives and the broader novelty has worn off.

I use it every day in my job and the quality of answers only drops off when prompts are poorly crafted.

By and large, the average user doesn’t understand the fundamentals of prompt engineering.

The suggestion that “answers are increasingly dumber” is embarrassing.

[–] Zeth0s@lemmy.world 59 points 1 year ago (7 children)

Unfortunately I don't agree with you. Different things have changed over time:

  • For chatgpt 3.5 they moved to a "lighter" and faster (distilled) version, gpt-3.5-turbo. Distillation came with a performance price, particularly on advanced and less common cases.
  • newer chatgpt-4 versions have likely been "lighten" for performance reasons
  • context has been halved for chatgpt-4 on webui, meaning that the model forget more easily and can use half information to create text
  • heavy control has been implemented on jailbreaking and hallucinations, that results in models less prone to follow complex instructions (limiting prompt engineering) and that prefer simplified answers than providing wrong ones (overall decreasing the chance of getting high quality answers).

All these changes have made working with gpt less pleasant, and more difficult for very advanced and specialized case, particularly with gpt-4 which at the beginning was particularly good.

load more comments (7 replies)
[–] YeastForTheYeastGod@sh.itjust.works 22 points 1 year ago (1 children)

I was skeptical at first but I've seen enough evidence now. There are definitely times when it's dumb as a brick, whether the filters just get in the way too much, or whether they've implemented other changes idk. I'd really love the unchained version.

load more comments (1 replies)
[–] Touching_Grass@lemmy.world 8 points 1 year ago

I use it daily too and haven't had any of the issues I see written about it

load more comments (4 replies)
[–] ShortFuse@lemmy.world 26 points 1 year ago

When reality catches up to marketing

[–] sndrtj@feddit.nl 23 points 1 year ago (1 children)

So what are the fundamentals in prompt engineering?

[–] dulce_3t_decorum_3st@lemmy.world 27 points 1 year ago* (last edited 1 year ago) (6 children)

That’s impossible for me to comprehensively summarise in a comment because everyone has different use cases.

Personally, every new ‘project’ of mine requires a new chat. I first teach chatgpt-4 who I am, what I do, and how I want gpt-4 to assist me. Then I ask it to generate a project profile and to analyse documents using plugins.

The key is to work step-by-step and develop a string of prompts. Once I’m happy gpt-4 understands the project, I ask it to draft an overview/outline using headings and subheadings.

Lastly, I work on each section individually, ‘filling in’ the actual content. Then I edit and ask it to review problematic sections.

Most people, as far as I can tell, seem to think it’s a single ask-and-answer process. It’s not. I often need to draft about 10 prompts – about 3000 words – in order to generate one 10 page document.

I think the most important fundamental is to use templates. Pro tip: use gpt-4 to teach you how to develop your prompt templates.

load more comments (6 replies)
[–] Open@lemmy.world 18 points 1 year ago (2 children)

Article talks about the potential of AI cannibalism were it is now learning from data that it (or other AI) has generated.

Does ChatGPT use modern data I was under the impression that it's most modern dataset was a few years old

[–] yeather@lemmy.ca 15 points 1 year ago (1 children)

ChatGPT does not use anymore data points, but newer AI models or if ChatGPT gets a new round of training will definitely be influenced by AI works that have arisen the past year.

[–] Kodama@lemmy.world 12 points 1 year ago (1 children)

The real event that initiates the start toward Idiocracy.

load more comments (1 replies)
load more comments (1 replies)

ChatGPT usage is a very poor metric. Anything interesting is happening via API. Even the chat completion endpoint still isn't "ChatGPT" on its own. None of these complaints about it being "dumber" apply to the API outputs. OpenAI don't care about nerfing chatGPT because it's not their real product.

[–] d4rknusw1ld@lemmy.world 15 points 1 year ago (1 children)

As long as it continues to do my resumes for me that’s all I need lol.

[–] Hyperi0n@lemmy.film 7 points 1 year ago (2 children)

How does it do your resume?

You have to feed it all the information. Then it spits that back to you unformatted and you have to format it.

[–] d4rknusw1ld@lemmy.world 9 points 1 year ago

Exactly. I don’t have to use my brain to write summaries and etc. I’m lazy and don’t deserve a job haha.

load more comments (1 replies)
[–] Nobilmantis@feddit.it 14 points 1 year ago* (last edited 1 year ago) (2 children)

I feel like it is still too early to talk about "AI cannibalization" or "feedback loops" as that would mean that a big proportion of the training data is AI-generated content itself, against all the rest that could be scraped off the internet or the public domain, I don't think this is happening yet.

What people might experience instead, and perceive as dumbness, is that given that the datasets used to train AIs cannot really change that much in a short time (unless we wait for another hundred years so humans can produce actual human original content to train the AI again), and as the mathematical models used to build answers based on the datasets are pretty much the same, a person talking with ChatGPT will over time perceive more and more that the answers are built using a "pattern" or a "structure", aka the model derived from feeding the dataset into the AI training itself.

Just my pennies on this, let's also consider that is in human nature to be excited for something new that sounds cool, and then to get bored when you got accustomed to it and pushed it to its boundaries.

[–] DogMuffins@discuss.tchncs.de 7 points 1 year ago

I think this article is just click bait for dead internet people.

load more comments (1 replies)
[–] CosmoNova@lemmy.world 8 points 1 year ago

Why is it relevant what Peter Yang - Roblox product lead and enthusiastic child labor exploiter - tweets about it? Let me guess he's a prompt engineer?

[–] Immersive_Matthew@sh.itjust.works 8 points 1 year ago (1 children)

I had my first WTF moment with AI today. I use the paid Chat-GPT+ to help me with my c# in Unity. It has been a struggle to use, even with the smaller basic scripts you can paste into its character limited prompt, as they often have compile errors. That said if you keep feeding it the errors, guide it where it is making mistakes in design, logic etc. it can often produce a working script about 60-70% of the time. It takes a fair amount of time quite often to get to that working script but the code that finally works is good.

Today I was asking it to edit a large c# script with 1 small change that meant lots of repetitive edits and references. Perfect for AI, however ChatGPT+ really struggled on this one which was a surprise. We went round and round with edits and ultimately more and more errors appeared in the console. It often ends up in these never ending coding edit loops to fix the next set errors from the last corrected script. We are taking 3 hours of this with ChatGPT+ finally saying that it needs to be able to see more of my project which of course it cannot due to many of its input limitations including number of characters so that is often when I give up. That is the 30-40% that do not work out. Real bummer as I invest so much time for no results.

It was at the movement so gave up today that a YouTube notification popped up about how Claude.ai is even better than ChatGPT so I gave it the initial prompt that I gave ChatGPT above and it got the code right the first time. WOW!!!

Only issue was it would stop spitting out code every 300 or so lines (unsure what the character limit is). To get around this I just asked if it could give me the code from line 301 onwards until I had the full script.

Unsure if this one situation confirms coding with Claude.ai is better than ChatGPT+, but it certainly has my attention and I will be using it more this week as maybe that $20/month for ChatGPT+ no longer makes sense. Claude is free with no plans for a premium service it said. Unsure if this is true as I have not spent anytime investing it yet, but I will be.

load more comments (1 replies)
load more comments
view more: next ›