That’s what I love about LLMs. They aren’t intelligent. They’re just really good at recognizing patterns. That’s why objective facts are always presented correctly. Most of the pattern points at the truth. To avoid this, they will have to add specific prompts to lie about this exact scenario. The next similar fact, they’ll have to manually code around that one too. LLMs are very good at finding the overwhelming truth.
Are you having this argument on the principle of defending the undergrounded-ness of bands, or do you actually believe LLMs always get the facts straight?
Eh, more of an exercise in scientific skepticism. It’s, possible that an obscure band with that name was mentioned deep in some training data that’s not going to come up in a search. LLMs certainly hallucinate, but not always.
But not 100%. And the things they hallucinate can be very subtle. That’s the problem.
If they are asked about a band that does not exist, to be useful they should be saying “I’m sorry, I know nothing about this”. Instead they MAKE UP A BAND, ITS MEMBERSHIP, ITS DISCOGRAPHY, etc. etc. etc.
But sure, let’s play your game.
All of the information on Infected Rain is out there, including their lyrics. So is all of the information on Jim Thirwell’s various “Foetus” projects. Including lyrics.
Yet ChatGPT, DeepSeek, and Claude will all three hallucinate tracks, or misattribute them, or hallucinate lyrics that don’t exist to show parallels in the respective bands’ musical themes.
So there’s your objective facts, readily available, that LLMbeciles are still completely and utterly fucking useless for.
So they’re useless if you ask about things that don’t exist and will hallucinate them into existence on your screen.
And they’re useless if you ask about things that do exist, hallucinating attributes that don’t exist onto them.
They. Are. Fucking. Useless.
That people are looking at these things and saying “wow, this is so accurate” terrifies the living fuck out of me because it means I’m surrounded not by idiots, but by zombies. Literally thoughtless mobile creatures.
Sounds like you haven’t tried an LLM in at least a year.
They have greatly improved since they were released. Their hallucinations have diminished to close to nothing. Maybe you should try that same question again this time. I guarantee you will not get the same result.
Their hallucinations have diminished to close to nothing.
Are you sure you’re not an AI, 'cause you’re hallucinating something fierce right here boy-o?
Actual research, as in not “random credulous techbrodude fanboi on the Internet” says exactly the opposite: that the most recent models hallucinate more.
Certainly! Here’s the English translation of the information about 凤凰血 (Blood of Phoenix):
🎸 About the Band / Project
“凤凰血” (Blood of Phoenix) is not a conventional live-performing band but rather the name of a 2016 EP by the Chinese extreme metal project ObscureDream. This is a one-man black metal/extreme metal project by Zhang Jiangnan (also known as Filth), who is also involved with other projects like Black Kirin and Dirtycreed.
🎵 EP: Blood of Phoenix (2016)
Release Date: April 16, 2016
Tracks:
Blood of Phoenix – approx. 5:50
Farewell to My Concubine – approx. 4:22
Blood of Phoenix (Instrumental) – approx. 4:50
Distribution: Released digitally via Bandcamp for about €2, available in MP3/FLAC formats.
🧱 Musical Style and Themes
The music blends black metal and death metal with traditional Chinese elements, such as epic atmospheres, folkloric themes, and historical references.
Tracks like Farewell to My Concubine reference iconic Chinese stories.
The sound is described as dark, intense, and cinematic, evoking a battlefield-like grandeur.
🎖 Reception and Influence
Blood of Phoenix marks an important shift for ObscureDream from raw black metal to a more refined blackened death metal sound.
It has been recognized as one of the “40 must-collect Chinese metal albums”.
International metal reviewers have praised it as a standout example of localized Chinese extreme metal with epic and national characteristics.
Summary
Blood of Phoenix isn’t a traditional band but a unique, culturally rich metal release by a Chinese solo artist. It stands out for merging extreme metal with Chinese historical and mythological motifs, gaining notable acclaim in both local and international underground metal scenes.
If you’d like links to listen, lyric translations, or analysis of the music/production, just let me know!
Huh. So there really is a 凤凰血. Weird how when I tried it (on several AIs) they just made shit up instead of giving me that information.
It’s almost like how you ask the question determines how it answers instead of, you know, using objective reality. Almost as if it has no actual model of objective reality and is just a really sophisticated game of mad-libs.
I asked ChatGPT to describe the abandoned railway line between Åkersberga and Rimbo, it responded with a list of stations and descriptions and explained the lack of photos and limited information as due to the stations being small and only open for a short while.
My explanation is that there has never been a railway line between Åkersberga and Rimbo directly, and that ChatGPT was just lying.
it’s not lying, because it doesn’t know truth. it just knows that text like that is statistically likely to be followed by text like this. any assumptions made by the prompt (e.g. there is an old railway line) are just taken at face value.
I use ChatGPT once a day or so. Yeah, it’s damned good at simple facts, more than lemmy will ever admit. Yeah, it’ll easily make shit up if there’s no answer to be had.
We should have started teaching tech literacy and objective analysis 20-years ago. FFS, by 2000 I had figured out that, “If it sounds like bullshit, it likely is. Look more.”
Also, after that post, I’m surprised this site hasn’t taken you out back and done an ol’ Yeller on ya. :)
That’s what I love about LLMs. They aren’t intelligent. They’re just really good at recognizing patterns. That’s why objective facts are always presented correctly. Most of the pattern points at the truth. To avoid this, they will have to add specific prompts to lie about this exact scenario. The next similar fact, they’ll have to manually code around that one too. LLMs are very good at finding the overwhelming truth.
Here’s me looking at the hallucinated discography of a band that never existed and nodding along.
Maybe they’re just way underground and you’ve never heard of them
I made the band up to see if LLMbeciles could spot that this is not a real band.
Feel free to look up the band 凤凰血, though, and tell me how “underground” it is.
Does this count?
Also, by nature of being underground they would be difficult to look up. Some bands have no media presence, not even a Bandcamp or a SoundCloud.
Are you having this argument on the principle of defending the undergrounded-ness of bands, or do you actually believe LLMs always get the facts straight?
Eh, more of an exercise in scientific skepticism. It’s, possible that an obscure band with that name was mentioned deep in some training data that’s not going to come up in a search. LLMs certainly hallucinate, but not always.
An obscure band with that name that has a discography that nobody’s ever heard of anywhere, complete with band member names, track titles, etc?
Yeah, pull the other one, Sparky. It plays “Jingle Bells”.
Nope.
You can tell because they’re not even in the same writing system. Future tip there.
Why would that matter? Band names are frequently translated and transliterated.
Dude. Go be reply guy somehwere else. You bore the fuck out of me.
Sure thing champ 👍 I’ll try to keep my responses to platforms designed for commenting
There are no objective facts about a band that never existed, that is the point.
Ask them about things that do have enough overwhelming information, and you will see it will be much more correct.
But not 100%. And the things they hallucinate can be very subtle. That’s the problem.
If they are asked about a band that does not exist, to be useful they should be saying “I’m sorry, I know nothing about this”. Instead they MAKE UP A BAND, ITS MEMBERSHIP, ITS DISCOGRAPHY, etc. etc. etc.
But sure, let’s play your game.
All of the information on Infected Rain is out there, including their lyrics. So is all of the information on Jim Thirwell’s various “Foetus” projects. Including lyrics.
Yet ChatGPT, DeepSeek, and Claude will all three hallucinate tracks, or misattribute them, or hallucinate lyrics that don’t exist to show parallels in the respective bands’ musical themes.
So there’s your objective facts, readily available, that LLMbeciles are still completely and utterly fucking useless for.
So they’re useless if you ask about things that don’t exist and will hallucinate them into existence on your screen.
And they’re useless if you ask about things that do exist, hallucinating attributes that don’t exist onto them.
They. Are. Fucking. Useless.
That people are looking at these things and saying “wow, this is so accurate” terrifies the living fuck out of me because it means I’m surrounded not by idiots, but by zombies. Literally thoughtless mobile creatures.
Sounds like you haven’t tried an LLM in at least a year.
They have greatly improved since they were released. Their hallucinations have diminished to close to nothing. Maybe you should try that same question again this time. I guarantee you will not get the same result.
Are you sure you’re not an AI, 'cause you’re hallucinating something fierce right here boy-o?
Actual research, as in not “random credulous techbrodude fanboi on the Internet” says exactly the opposite: that the most recent models hallucinate more.
Certainly! Here’s the English translation of the information about 凤凰血 (Blood of Phoenix):
🎸 About the Band / Project
“凤凰血” (Blood of Phoenix) is not a conventional live-performing band but rather the name of a 2016 EP by the Chinese extreme metal project ObscureDream. This is a one-man black metal/extreme metal project by Zhang Jiangnan (also known as Filth), who is also involved with other projects like Black Kirin and Dirtycreed.
🎵 EP: Blood of Phoenix (2016)
Release Date: April 16, 2016
Tracks:
Blood of Phoenix – approx. 5:50
Farewell to My Concubine – approx. 4:22
Blood of Phoenix (Instrumental) – approx. 4:50
Distribution: Released digitally via Bandcamp for about €2, available in MP3/FLAC formats.
🧱 Musical Style and Themes
The music blends black metal and death metal with traditional Chinese elements, such as epic atmospheres, folkloric themes, and historical references.
Tracks like Farewell to My Concubine reference iconic Chinese stories.
The sound is described as dark, intense, and cinematic, evoking a battlefield-like grandeur.
🎖 Reception and Influence
Blood of Phoenix marks an important shift for ObscureDream from raw black metal to a more refined blackened death metal sound.
It has been recognized as one of the “40 must-collect Chinese metal albums”.
International metal reviewers have praised it as a standout example of localized Chinese extreme metal with epic and national characteristics.
Summary
Blood of Phoenix isn’t a traditional band but a unique, culturally rich metal release by a Chinese solo artist. It stands out for merging extreme metal with Chinese historical and mythological motifs, gaining notable acclaim in both local and international underground metal scenes.
If you’d like links to listen, lyric translations, or analysis of the music/production, just let me know!
https://coldwoodsprod.bandcamp.com/album/blood-of-phoenix
Huh. So there really is a 凤凰血. Weird how when I tried it (on several AIs) they just made shit up instead of giving me that information.
It’s almost like how you ask the question determines how it answers instead of, you know, using objective reality. Almost as if it has no actual model of objective reality and is just a really sophisticated game of mad-libs.
Almost.
This was the first result I got, but I passed it by since it’s not actually a band.
I asked ChatGPT to describe the abandoned railway line between Åkersberga and Rimbo, it responded with a list of stations and descriptions and explained the lack of photos and limited information as due to the stations being small and only open for a short while.
My explanation is that there has never been a railway line between Åkersberga and Rimbo directly, and that ChatGPT was just lying.
Claude’s reply:
Perfectly accurate!
it’s not lying, because it doesn’t know truth. it just knows that text like that is statistically likely to be followed by text like this. any assumptions made by the prompt (e.g. there is an old railway line) are just taken at face value.
also, since there has indeed been a railway connection between them, just not direct, that may have been part of the assumption.
I expected it to talk about the actual railway, not invent a fantasy line
I use ChatGPT once a day or so. Yeah, it’s damned good at simple facts, more than lemmy will ever admit. Yeah, it’ll easily make shit up if there’s no answer to be had.
We should have started teaching tech literacy and objective analysis 20-years ago. FFS, by 2000 I had figured out that, “If it sounds like bullshit, it likely is. Look more.”
Also, after that post, I’m surprised this site hasn’t taken you out back and done an ol’ Yeller on ya. :)
I was told we weren’t allowed to do that anymore
Of course you were told that.
LLMentalist