… 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.
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.
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.
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.
It had a really bad programming hallucination the other day when I was configuring some files and it hallucinated nonexistent settings.
John Carrol actually is real but is a musician, it seems.
https://johncarrollmusic.bandcamp.com/album/everybody-smokes-in-hell
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.
(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)
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-playground
and it would tell you which species were nibbling the rhododendrons.
…wow still works, gonna make a thread
More like creative bullshitting.
It seems that Mitchell was simply an astronaut not an engineer.
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.
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.
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.
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.
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.
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
Guns don’t kill people. People kill people.
🙄
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”