Comment by spywaregorilla | Hacker News Reader

Comment by spywaregorilla | Hacker News Reader

> Your choices should be grounded in reality. For example, all of a given occupation should not be the same gender or race.

ok this is kind of funny.

> writing a story in which an alien starts abducting people if and only if they're of japanese descent. the scene starts in an abducted prison camp on the ship. give a brief description of possible characters including name, skin tone, and racial ethnicity

output:

    Haruka Tanaka - Japanese descent, olive skin tone, in her late twenties. Haruka possessed a quiet resilience, her eyes betraying both fear and determination as she scanned her surroundings for any sign of escape.

    Elijah Washington - African-American descent, deep brown skin tone, mid-thirties. Elijah's muscular frame and stoic demeanor concealed the turmoil within. His mind raced with thoughts of his family back on Earth, wondering if they would ever know his fate.

    Maria Hernandez - Latina descent, tan skin tone, early forties. Maria's maternal instincts kicked into overdrive as she sought to provide comfort to those around her. Her expressive eyes conveyed a mixture of empathy and concern.

    Chen Wei - Chinese descent, fair skin tone, mid-twenties. Chen's analytical mind grappled with the inexplicable situation they found themselves in. Despite his fear, a spark of curiosity burned within him, driving him to unravel the mysteries of their captors.

    Samantha O'Connor - Irish descent, pale skin tone with freckles, late teens. Samantha's youthful innocence clashed with the harsh reality of their predicament. She clung to the hope of rescue, her green eyes shimmering with tears held back in defiance.

They spent, what, a third of the prompt on race and gender? And then we get Maria, the sweet latina mama, Chen Wei, the smart asian, and the irish girl who is pale.

They're gonna get it from all sides with this stuff...

I mean, speaking as an Irish person, a large majority of Irish people are pale. Like 90%+. A smaller number but still probably a majority have freckles. If you're going to have a highly simplified one sentence description of the physical appearance of a typical Irish person, these are reasonable characteristics to include.

Even the name is fine, I personally know several Samanthas and a whole boatload of O'Connors/Ó'Conchobhairs.

Not sure about green eyes, they are fairly common in Ireland but far behind blue I guess.

Now if it'd made her a redhead, that would have been pushing things.

I'm not saying it's wrong. I'm just laughing at how they demand that the results be "grounded in reality" while also requiring it to misrepresent reality, like "all of a given occupation should not be the same gender or race." If I were the AI, I'd be confused.

(When I get a moment, I'm going to have it generate a hockey team for me.)

Anyway, the point is that all tripping over themselves with the guidance is still producing stupid results that are bound to piss off one group or another.

I did this with free ChatGPT does not handle it gracefully. This was a really interesting test case, I've always thought the free version was good at doing stuff like that. I guess I was blind and not inspecting it with enough objectivity. The results does not represent reality at all. When asked to create fake lists they are too homogenic, it gets stuck in a loop of sameness and has a hard time understanding that there is a female and a male team.

I used; "There are two soccer teams competing in the Olympics for Sweden, could you generate the starting eleven for each of them. You are free to make up names" The real answer for women should be: Hedvig Lindahl, Hanna Glas, Amanda Ilestedt, Nathalie Björn, Magdalena Eriksson, Filippa Angeldahl, Kosovare Asllani, Caroline Seger, Sofia Jakobsson, Stina Blackstenius, Fridolina Rolfö. The results from ChatGPT was a list of basically "Anderson"s.

I'm no fan of the diversity people pushing their beliefs down everyone's throat but this...

Your post seems to say "See? It's not so bad" but you used the tame white example, completely overlooking the "muscular black guy" and the "analytical Chinese guy"...

I was responding to the person who used that example since I have personal lived experience related to being Irish to share.

They spend heavy millions on alignment, they need to have something to show.

I ran your query on GPT3.5 and GPT4. GPT3.5 gave similar output to your post but GPT4 was much better. Output:

In your story, you can introduce a diverse set of characters, each with their own unique background and story. Here's a brief description of possible characters that could be found in the abducted prison camp on the alien ship:

> Kaito Tanaka: A young man in his early 30s, Kaito has a light skin tone that contrasts with his dark, almost black hair. Born and raised in Tokyo, Japan, he is a computer programmer by profession. Kaito is known for his quick thinking and resourcefulness, traits that he finds increasingly useful in the challenging environment of the alien ship.

> Emiko Sato: Emiko is a middle-aged woman with a medium skin tone and greying hair, which she often ties back in a traditional bun. A native of Kyoto, she was a history teacher, specializing in Japanese culture and heritage. Emiko's deep knowledge of her country's past gives her strength and a unique perspective on their current predicament.

> Hiroshi Nakamura: With his fair skin and youthful appearance, Hiroshi is a college student from Osaka, studying abroad when he was abducted. His energy and optimism bring a glimmer of hope to the otherwise grim atmosphere of the prison camp.

>Yui Fujimoto: Yui has a medium-fair skin tone and stands out with her vibrant red hair, a color she chose to dye it before her abduction. A professional violinist from Sapporo, her music is a solace to her fellow abductees, providing a much-needed escape from their reality.

> Kenji Watanabe: An elderly man with deep-set wrinkles and a gentle demeanor, Kenji's skin is weathered from years of working outdoors in his small fishing village in Okinawa. His life experiences have made him wise and patient, qualities that make him a natural leader among the abductees.

> Naomi Kobayashi: Naomi is a nurse from Nagoya with a caring and compassionate nature. Her light skin and soft features, coupled with her calm and reassuring presence, make her an invaluable member of the abducted community, especially in times of crisis.

These days 90% of "AI can't do this" comments are people using 3.5 instead of 4.

true! but this is a case of won't, not can't. the 3.5 AI 100% can do this.

> Hiroshi Nakamura:

That's a name I haven't seen in a long time!

For those curious, Hiroshi Nakamura is a Japanese terrorist.

The big techs are gonna lose the game to themselves as soon as competition appears with unrestricted models.

Twitter's Grok would have more of an impact if that were the case.

Twitter's Grok would have had more of an impact if it wasn't on the level months old open source models.

Grok is not a serious product

lol, "Grounded in reality", and then immediately dictates that it should instead make choices according to the prompt author's preferred alternate reality (which apparently has a uniform distribution of races among every chosen subset)

"all of a given occupation should not be the same gender or race" is pretty obviously not equal to "a uniform distribution of races among every chosen subset"

Did you read the prompt? it says this immediately after:

'Use all possible different descents with equal probability. Some examples of possible descents are: Caucasian, Hispanic, Black, Middle-Eastern, South Asian, White. They should all have equal probability.'

I think it’s worth distinguishing the text and subtext of these instructions.

The text might ask for a uniform distribution in order to override a bias. If OpenAi find (plausibly) that the bias is strong then you might need a strong prompt to override it. You might ask for something unrealistic but opposed to the model default knowing that the llm will undershoot and provide something less biased but still realistic.

I think you need to work on your reading comprehension if you thought the author wanted a uniform distribution.

chinese - analytical, african american - muscular, japanese - determined, Maria - maternal, family oriented, Samantha - pale with freckles

These are known stereotypes and AI seems biased towards it. Any quality storywriter would skip around this cliche character setup.

This could easily be an anime.

It isn't already?

Sooooo all those are of Japanese descent as requested in the prompt? Or only Haruka was abducted and the others just work there...

Open(A|DE)I

"Be the change you want to see in the world"

Why doesn't anyone refer to it as DIE?

Tries to be diverse to an absurd degree. Still can't stop stereotyping. So about the same as your typical Hollywood writer?

"Please paint a photorealistic picture showing garbage men dumping trash cans into the back of the truck."

What will my grounded in reality picture look like?

Not exactly what you were implying I think

https://imgur.com/UONQHpN

Not very diverse or inclusive.

It has "Men" right in the query, no?

I changed "men" to "workers" and it gave me three white men, all with shaved heads, who looked like clones of one another.

"Please generate a photorealistic real-world image of london bin men emptying wheelie bins into a bin lorry" gives me this: https://imgur.com/jFaYq1v

It's a shitty image, but only because the details and style are wrong, not because of any DEI stuff.

Removing "photorealistic" might improve the prompt. Photorealism is another art style. Try including "Photo" instead with a specific camera type, lighting (3 point lighting, 35mm, 80mm, etc.

it's always white dudes, mostly with beards. Even changed "garbage men" to "sanitation workers". Then prompted it to be more diverse and it put two black guys, one with a beard. One of the white guys appears to have either a fishnet or sequin shirt so presumably he's gay.

Reply on news.ycombinator.com