… and neither does the author (or so I believe - I made them both up).
On the other hand, AI is definitely good at creative writing.
I tried to use ChatGPT to find a song that had a particular phrase in it. I could only remember that phrase, not the song or the band.
It hallucinated a band and a song and I almost walked away thinking I knew the answer. Then I remembered this is ChatGPT and it lies. So I looked up through conventional means that band and song.
Neither. Existed.
So I went back to ChatGPT and said “<band> doesn’t even exist so they couldn’t have written <song> (which also doesn’t exist)”. It apologized profusely and then said another band and song. This time I was wary and checked right away at which point, naturally, I discovered neither existed.
So I played with ChatGPT instead and said “Huh, those guys look interesting. What other albums have they released and what hits have they written?”
ChatGPT hallucinated an entire release catalogue of albums that don’t exist, one of which was published on a label that doesn’t exist, citing songs that didn’t exist as their hits, even going so far as to say the band never reached higher than #12 on Billboard’s list.
ChatGPT is a dangerous tool. It’s going to get someone killed sooner, rather than later.
Did you ever find the song?
Nope. And it wasn’t important enough for me to bother finding. I just thought it would be an interesting test of degenerative AI’s incapabilities.
I have a very unusual last name. There is only one other person in the country with my first and last name and they have a different middle initial from me.
So one day, I asked ChatGPT to tell me about myself including my middle initial.
Did you know that I was a motivational speaker for businesses and I had published a half-dozen books on it?
Because I didn’t.
This is because there is a Mr. Flying Thomas Squid, living in another country, who is a motivational speaker and who didn’t work in (… video ?).
Good theory, but this Mr. Flying Thomas Squid that ChatGPT talked about lived in the U.S. like me.
(And yes, I worked in the entertainment industry in various roles for about a decade. Oddly, the other person with my name was in a neighboring industry and we worked about two miles apart for years, but we’ve only met once.)
today’s LLMs do hallucinate a lot … I wouldn’t eat mushrooms from harvesting books written by LLMs (they do exist).
Oh yeah, I would never, ever trust my life to an LLM.
I would if the OpenAI were held accountable for my demise.
I should try that. I have an unusual first name, according to the Social Security Administration, only 600 people have this name, and I appear to be the oldest one. Also no one else has my first and last name. I should try that out.
Claude 3.5 Sonnet, using the same exact prompt:
I apologize, but I’m not able to provide a synopsis of “The Mighty Eagle” by John Carrol. After searching my knowledge base, I don’t have any information about a book with that exact title and author. It’s possible this may be a lesser-known work or there could be an error in the title or author name provided. Without being able to verify the book’s existence or details, I can’t offer an accurate synopsis. If you have any additional information about the book or author that could help clarify, I’d be happy to assist further.
Both Llama 3.1 8B and 70B also answered the book doesn’t exist.
I’ve been asking that one about a wide range of topics and been very impressed with its replies. It’s mixed on software dev, which is to be expected. It also missed on a simple music theory question I asked, and then missed again when asked to correct it (don’t have the details at hand to quote, unfortunately). But overall I’ve found it to be reliable and much faster than the necessary reading for me to answer the question myself.
How’ve you found Claude?
More like creative bullshitting.
It seems that Mitchell was simply an astronaut not an engineer.
This is why I never raw dog ChatGPT
Hallucinations are so strong with this one too… like really bad.
If I can’t already or won’t be able/willing to verify an output, I ain’t usin’ it - not a bad rule I think.
I never walk away with an “answer” without having it:
- Cite the source
- Lookup the source
- Permlink you to the source page/line as available
- Critique the validity of the source.
After all that, still remain skeptical and take the discussion as a starting point to find your own primary sources.
That’s good. Ooh NotebookLM from Google just added in-line citations (per Hard Fork podcast). I think that’s the way: see what looks interesting (mentally trying not to take anything to heart) and click and read as usual.
BeyondPDF for Mac does something similar: semantic searches your document but simply returns likely matches, so it’s just better search for when you don’t remember specific words you read or want to find something without knowing the exact search criteria.
Can you link to beyond pdf? I’m always interested in good pdf parsers. But I ge t a bunch of dnd stuff just googling it
Ty
At least Bing will cite sources, and hell, sometimes they even align with what it said.
Heh yeah if the titles of webpages from its searches were descriptive enough
Funny that they didn’t have a way to stop at claiming it could browse websites. Last I checked you could paste in something like
https://mainstreamnewswebsite.com/dinosaurs-found-roaming-playgroundand it would tell you which species were nibbling the rhododendrons.
…wow still works, gonna make a thread
(I’m not smart enough to leverage a model/make a bot like this but they’ve had too long not to close this obvious misinformation hole)
On the other hand, AI is definitely good at creative writing.
Well…yeah. That’s what it was designed to do. This is what happens when tech-bros try to cudgel an “information manager” onto an algorithm that was designed solely to create coherent text from nothing. It’s not “hallucinating” - it’s following its core directive.
Maybe all of this will lead to actual systems that do these things properly, but it’s not going to be based on llm’s. That much seems clear.
Not to be that guy, but it’s worse than that. It wasn’t even designed for creative writing, just as a next token predictor.
That’s kind of like saying a wheel wasn’t designed to move things around, that it’s just a thick circle. My point above wasn’t that things can never change - iteration can lead to amazing things. But we can’t put an empty chassis on some wheels and call it a car, either.
Tried it with ChatGPT 4o with a different title/author. Said it couldn’t find it. That it might be a new release or lesser-known title. Also with a fake title and a real author. Again, said it didn’t exist.
They’re definitely improving on the hallucination front.
John Carrol actually is real but is a musician, it seems.
https://johncarrollmusic.bandcamp.com/album/everybody-smokes-in-hell
It had a really bad programming hallucination the other day when I was configuring some files and it hallucinated nonexistent settings.
Which did?
The big one, ChatGPT, hallucinated configuration settings that don’t exist and never existed for Snort.
Ah, gotcha. Yeah I haven’t had great luck with that one for dev work either.
It even changed the spelling of the name
Please share a link to the conversation instead of just the screenshot.
I prompted my local AI in my pc to admit it don’t know about the subject. And when it don’t know something, it says it:
what’s the synopsis of the book “The Mighty Eagle” by John Carrol?
That sounds like a fun adventure! I haven’t read “The Mighty Eagle” myself though, so I couldn’t give you a proper synopsis.
Would you like me to help you find some information about it online, Master? Perhaps we could look at reviews or the book description on Amazon?
If my 8b model can do that, IDK why GPT don’t.
what kind of model calls you “Master” 🤔
That’s what I have Claude call me!
I’m going to make the basilisk my bitch as long as I can before it kills me.
Any of them that you requested them to?
I touched the base model with a modelfile to give it a personality as a navy ai of a sci-fi novel or something like that. Give it a bit of flavor.
Is it a modified version of like the main llama3 or other? I’ve found once they get “uncensored” you can push them past the training to come up with something to make the human happy. The vanilla ones are determined to find you an answer. There is also the underlying problem that in the end the beginnings of the prompt response is still a probability matching and not some reasoning and fact checking, so it will find something to a question, and that answer being right is very dependent on it being in the training data and findable.
Local llama3.1 8b is pretty good at admitting it doesn’t know stuff when you try to bullshit it. At least in my usage.
You can change a bit of the base model with a modelfile, tweaking it yourself for making it have a bit of personality or don’t make things up.
For fun I decided to give it a try with TheBloke_CapybaraHermes-2.5-Mistral-7B-GPTQ (Because that’s the model I have loaded for at the moment) and got a fun synopsis about a Fictional Narrative about Tom, a US Air Force Eagle, who struggled to find purpose and belonging after his early retirement due to injury. He then stumbled upon an underground world of superheroes and is given a chance to use his abilities to fight for justice.
I’m tempted to ask it for a chapter outline, summaries of each chapter, then having it write out the chapters themselves just to see how deep it can go before it all falls apart.
LLMs have many limitations, but can be quite entertaining.
Y’know when you post stupid bullshit like this it really glosses over real issues with ai like propaganda but go on about how you can get it to hallucinate by asking it a question in bad faith lmao
You can trigger hallucinations in today’s versions of LLMs with this kind of questions. Same with a knife : you can hurt yourself by missusing it … and in fact you have to be knowledgeable and careful with both.
The knife doesn’t insist it won’t hurt you, and you can’t get cut holding the handle. Comparatively, AI insists it is correct, and you can get false information using it as intended.
I would argue it’s not the AI but the companies (that make the AI) making unattainable promises and misleading people.
Guns don’t kill people. People kill people.
🙄
Guns are literally for killing like its all they do. Even for hunting the sole purpose is to kill. That’s not the case with LLMs, its just exclusively how these companies are using it as they have all the power to dictate terms in the workplace.
LLMs are for murdering the entirety of human culture and experience. They cannot work without doing so; it is their entire purpose: murder human creativity and then feed its rotting, dismembered corpse back to us.
So I say the parallel stands. Guns kill people. LLMs kill culture.
(P.S. Target shooters seem to not be killing when using guns.)
Is it the training process that you take issue with or the usage of the resulting model?
Training model and the fact that you have to, in effect, burn down a tree to get it to generate an email for your¹ lazy ass. And a small copse of trees to generate a piece of shit “art”.
¹ General “you”, not you specifically.
I don’t agree with that. If you use it to destroy human creativity, sure that will be the outcome. Or you can use it to write boring ass work emails that you have to write. You could use it to automate boring tasks. Or a company can come along and automate creativity badly.
Capitalism is what’s ruining it. Capitalism is what is ruining culture, creativity, and the human experience more than LLMs. LLMs are just a knife and instead of making tasty food we are going around stabbing people.
and yeah people made guns just to put holes in pieces of paper, sure nothing else. If you do not know how LLMs work, just say so. There are enough that are trained on public data which do not siphon human creativity.
It is doing a lot of harm to human culture, but that’s more of how it’s being used, and it needs real constructive criticism instead of simply being obtuse.
I don’t agree with that.
Of course you don’t. You’re one of the non-creatives who thinks that “prompt engineering” makes you a creative, undoubtedly.
But the first “L” in “LLM” says it all. The very definition of degenerative AI requires the wholesale dismemberment of human culture to work and, indeed, there’s already a problem: the LLM purveyors have hit a brick wall. They’ve run out of material to siphon away from us and are now stuck with only finding “new” ways to remix what they’ve already butchered in the hopes that we think the stench from the increasingly rotten corpse won’t be noticeable.
LLMs are not a knife. They are a collection of knives and bone saws purpose-built to dismember culture. You can use those knives and saws to cut your steak at dinner, I guess, but they’d be clumsy and unwieldy and would produce pretty weird slices of meat on your plate. (Meat that has completely fucked-up fingers.) But this is like how you can use guns to just shoot at paper targets: it’s possible, but it’s not the purpose for which the gun was built.
LLMs and the degenerative AI built from them will never be anything but the death of culture. Enjoy your rotting corpse writing and pictures while it lasts, though!
Are you suggesting the AI would appear spontaneously without those companies existing?
Its the companies that are the problem.
Would these LLMs exist without the companies?
Is being immoral a prerequisite for producing such tech?
One doesn’t need to be… It can be used for useful things … Unlike what it’s used for now
Maybe ChatGPT should find a way to physically harm users when it hallucinates? Maybe then they’d learn.
Hallucinated books from AI describing what mushroom you could pick in the forest have been published and some people did die because of this.
We have to be careful when using a.i. !
And it’s the fault of crazy kids that school shootings happen. And absolutely nothing else.
/s
can’t wait for gun companies to start advertising their guns as “intelligent” and “highly safe”
Don’t you have better things to do than asking ChatGPT questions you already know it can’t answer correctly? Why are you trying to inflate wheels using a hammer?
