Chat GPT AI

  • Guest, it's time once again for the massively important and exciting FoH Asshat Tournament!



    Go here and give us your nominations!
    Who's been the biggest Asshat in the last year? Give us your worst ones!

Tuco

I got Tuco'd!
<Gold Donor>
47,812
82,235
Looks like jmal9000 was banned, oh well. We talked a bit ago about generating standup with GPT. I got access to GPT 4o and gave it a shot of a throwaway joke I heard from Chapelle once.

Please write a script for a stand-up comedy bit. The script should express that the comedian is mad at the city of Los Angeles and after a bad show, the comedian spends their entire paycheck for the show to buy bubble gum, hands it out to the homeless so they can chew all night but still be hungry. The script should be clever and slightly angry, while being inspired from the writing from stand-up comedians like Dave Chappelle, Bill Burr, Louis CK, Chris Rock, Eddie Murphy and Sam Kinison.



(Comedian walks onto the stage with a slightly agitated look, holding a small paper bag)
Good evening, folks. How’s everyone doing tonight? Yeah, I’m not too great. Just had a show in Los Angeles, and let me tell you, that city... that city can kiss my ass.
I mean, have you been to LA? It’s like someone took a city and decided to make it out of Botox and broken dreams. The traffic alone makes you question your will to live. You ever been stuck on the 405 for so long you start rethinking every decision you’ve ever made? Like, why did I even come here? Why did I ever leave my hometown? Why did I agree to this gig?
So, I did this show, right? And it bombed. It BOMBED. It was so bad, I think the ghosts of failed auditions past showed up just to boo me. You know it's bad when the hecklers don’t even bother. They just look at you like, “Wow, buddy, you’re suffering enough.”
So after this catastrophe of a show, I get my paycheck. And you know what? I looked at that check, and it was just enough to make me feel insulted. Like, it wasn’t even “thanks for trying” money. It was “please go away” money.
So what do I do? I took that check, and I said, "Screw it. I’m gonna spend it all on something completely pointless." Something that would encapsulate my rage and disappointment with this godforsaken city. So I went to a convenience store and bought... all the bubble gum. ALL OF IT. Every last piece. The cashier looked at me like I was out of my mind. “Are you sure you want all this gum?” she asked. And I said, “Lady, I’ve never been more sure of anything in my life.”
(Comedian pulls out packs of gum from the paper bag and shows it to the audience)
Yeah, so now I’ve got all this gum. And I’m walking around downtown LA, just angry and chewing like a maniac. Then I see the homeless. And LA has a lot of homeless. Like, if they had a census, it would just be a guy holding a clipboard, asking, “Homeless or not?”
And here’s the thing—these people are down and out. And in my twisted, frustrated mind, I think, “You know what? I’m gonna share this gum.” Because nothing says “I’m here for you” like giving someone something completely useless when they’re starving. So I start handing out packs of gum to the homeless.
“Here you go, buddy. Have some gum. Chew all night, but still be hungry.”
And they’re looking at me like, “Really, dude? Gum? You couldn’t get a sandwich or something?” And I’m like, “Nope, just gum. Enjoy the spearmint. Maybe blow a bubble and forget your troubles for a second.”
But here’s the kicker: they actually took it. Some of them even smiled. Because in that moment, it wasn’t about the gum. It was about someone acknowledging them. It was about sharing in the absurdity of this ridiculous city where the glitz and glam can’t hide the grit and grime.
So here’s to you, LA. Thanks for the material. Thanks for the traffic, the broken dreams, and the opportunity to give out the world’s most impractical gift to those who need it least. I’ll see you on the 405, you miserable, beautiful mess of a city.
(Comedian throws a few packs of gum to the audience and walks off stage)
Thank you, goodnight!

Thank you. Please rewrite the bit to stress that the comedian purchased the gum specifically to give to the homeless to spite the city intentionally. Also rewrite that the comedian's performance in Los Angeles was good, but the city's response was poor and deserving of the comedian's anger.



(Comedian walks onto the stage with a slightly agitated look, holding a small paper bag)
Good evening, folks. How’s everyone doing tonight? Yeah, I’m not too great. Just had a show in Los Angeles, and let me tell you, that city... that city can kiss my ass.
I mean, have you been to LA? It’s like someone took a city and decided to make it out of Botox and broken dreams. The traffic alone makes you question your will to live. You ever been stuck on the 405 for so long you start rethinking every decision you’ve ever made? Like, why did I even come here? Why did I ever leave my hometown? Why did I agree to this gig?
So, I did this show, right? And it was good. It was GOOD. I was on fire, folks. The jokes were landing, the energy was electric. I was thinking, “Damn, I’m killing it tonight.” But the audience? They were colder than an ex’s heart. Sitting there with their Botoxed faces, barely cracking a smile. You know it's bad when the hecklers don’t even bother. They just look at you like, “Wow, buddy, you’re suffering enough.”
So after this infuriating show, I get my paycheck. And you know what? I looked at that check, and it was just enough to make me feel insulted. Like, it wasn’t even “thanks for trying” money. It was “please go away” money.
So what do I do? I took that check, and I said, "Screw it. I’m gonna spend it all on something completely pointless. Something that would encapsulate my rage and disappointment with this godforsaken city." So I went to a convenience store and bought... all the bubble gum. ALL OF IT. Every last piece. The cashier looked at me like I was out of my mind. “Are you sure you want all this gum?” she asked. And I said, “Lady, I’ve never been more sure of anything in my life.”
(Comedian pulls out packs of gum from the paper bag and shows it to the audience)
Yeah, so now I’ve got all this gum. And I’m walking around downtown LA, just angry and chewing like a maniac. And then it hit me: LA doesn’t deserve my respect. No, I’m gonna spite this city. I see the homeless people, and I think, “You know what? I’m gonna do something that embodies the insanity of LA.” So I start handing out packs of gum to the homeless. Not out of kindness, no. Out of spite.
“Here you go, buddy. Have some gum. Chew all night, but still be hungry.”
And they’re looking at me like, “Really, dude? Gum? You couldn’t get a sandwich or something?” And I’m like, “Nope, just gum. Enjoy the spearmint. Maybe blow a bubble and forget your troubles for a second.”
But here’s the kicker: they actually took it. Some of them even smiled. Because in that moment, it wasn’t about the gum. It was about sharing in the absurdity of this ridiculous city where the glitz and glam can’t hide the grit and grime.
So here’s to you, LA. Thanks for the material. Thanks for the traffic, the broken dreams, and the opportunity to give out the world’s most impractical gift to those who need it least. I’ll see you on the 405, you miserable, beautiful mess of a city.
(Comedian throws a few packs of gum to the audience and walks off stage)
Thank you, goodnight!
 

Captain Suave

Caesar si viveret, ad remum dareris.
5,323
9,033
Are the models at the point they could take a piece of art and make a 3D walkable representation of it in unreal 5? Would be cool if say someone knit together all the works of cezanne or hr giger into an actual virtual world you can walk around in

tldw; Inverse ray tracing to generate 3d models and material descriptions from images.

 

Pasteton

Blackwing Lair Raider
2,810
1,958
When will we have access to these things? I wouldn’t mind shitting out 3D models when I’m bored, then maybe make a dungeon in unreal 5 with them
 

Captain Suave

Caesar si viveret, ad remum dareris.
5,323
9,033
When will we have access to these things? I wouldn’t mind shitting out 3D models when I’m bored, then maybe make a dungeon in unreal 5 with them

You can download the papers, models, and source code from links in the video. I expect it would be a year or two before this stuff starts popping up in commercial applications.
 

Control

Bronze Baronet of the Realm
3,111
8,228
When will we have access to these things? I wouldn’t mind shitting out 3D models when I’m bored, then maybe make a dungeon in unreal 5 with them
I think for almost all game-ish purposes, stuff from the asset store is going to be much more useful for the foreseeable future. Things like this may help asset creators work much faster though. If you want a crappy version of your living room in-game to run around in then sure, although you can already do that with some scanning/photogrammy apps. I guess this is just an iteration on those?
 

Daidraco

Avatar of War Slayer
10,332
10,751
I think for almost all game-ish purposes, stuff from the asset store is going to be much more useful for the foreseeable future. Things like this may help asset creators work much faster though. If you want a crappy version of your living room in-game to run around in then sure, although you can already do that with some scanning/photogrammy apps. I guess this is just an iteration on those?
This is what I thought about most of that demo. Feet like I watched some stupid game dev shit about where they were taking like 200 pictures and turning it into a real life 3D model for the game.

Other than the automatic creation of 3d models from flat images?
I guess that is the base idea, there. I was caught up in the reverse shadows thing for some reason.
 
  • 1Like
Reactions: 1 user

Lolkaitis

Golden Squire
19
7
Looks like the new Claude Sonnet 3.5 you can't ask it to write it under the prose of authors because it talks about it can't do copyrighted works. But if you use Claude Opus you can.
 

Lolkaitis

Golden Squire
19
7
I made a game with Sonnet 3.5 that if you guys want to try out and play.

You enter a word, the word is flashed with the corresponding numbers associated with the letters, you then select an above prediction (lowest number you guess it is) and after that select a below prediction (highest number you guess it is) and then finally select what you estimated or predict the word sum value is, between the highlighted cells for the above and below prediction.

Word Sum Prediction Game

I suggest playing it on phone but you can play from PC.

It's a game I've had on my mind for +4 years, just never knew how to code. Finally I can make it with GPT.
 
Last edited:
  • 1Moron
  • 1Like
Reactions: 1 users

Mist

REEEEeyore
<Gold Donor>
31,371
23,792
I made a game with Sonnet 3.5 that if you guys want to try out and play.

You enter a word, the word is flashed with the corresponding numbers associated with the letters, you then select an above prediction (lowest number you guess it is) and after that select a below prediction (highest number you guess it is) and then finally select what you estimated or predict the word sum value is, between the highlighted cells for the above and below prediction.

Word Sum Prediction Game

I suggest playing it on phone but you can play from PC.

It's a game I've had on my mind for +4 years, just never knew how to code. Finally I can make it with GPT.
How does this require AI in any way? Seems like a phish or something.
 
  • 1Salty
Reactions: 1 user

Lolkaitis

Golden Squire
19
7
How does this require AI in any way? Seems like a phish or something.

I don't code that well. Its a game concept that I wanted to design for a long time. It's pretty simple game to be honest. You have screen 1) word flash with numbers, you make a quick mathematical guess based on what you absorb. Screen 2) A grid where you select prediction values and screen 3) Your calculated prediction score value.

It's a basic version of the game I want to make. I plan on adding a lot more bells and whistles.
 
  • 1Like
Reactions: 1 user

Lolkaitis

Golden Squire
19
7
I wanted to first test Claude Sonnet 3.5 with it calculating word sum values. By making it associate the alphabet a-z with 1-26. Then computing the possible letter combinations that make real words that have the word sum value of 49. Claude Sonnet 3.5 failed and hallucinated math with this one. I'm not posting the hallucinations so I decided to test the LLM with something I think it would excel at. Here:


I want you to list 4 words off that could be related to the 1 word, so 5 words that relate to the 1st used word. Then I want you to take the 5th word that is listed and list 4 words that relate to it. I want you to rinse repeat this 10 times. I want all the words to be separated by comma and a space, followed by next word with a comma after it and a space again. I want to see how you are good with generating this word game with your LLM capabilities. Do this 25 times.

  • Ocean, waves, blue, fish, beach,
  • Beach, sand, sunscreen, umbrella, volleyball,
  • Volleyball, net, team, court, serve,
  • Serve, waiter, restaurant, food, menu,
  • Menu, options, choices, dishes, prices,
  • Prices, cost, value, economy, inflation,
  • Inflation, economy, currency, money, bank,
  • Bank, account, savings, loan, teller,
  • Teller, story, book, author, plot,
  • Plot, narrative, characters, conflict, resolution,
  • Resolution, solution, problem, goal, determination,
  • Determination, willpower, motivation, perseverance, success,
  • Success, achievement, accomplishment, victory, celebration,
  • Celebration, party, cake, balloons, birthday,
  • Birthday, age, candles, presents, anniversary,
  • Anniversary, milestone, marriage, couple, romance,
  • Romance, love, relationship, passion, date,
  • Date, calendar, time, schedule, appointment,
  • Appointment, doctor, health, checkup, clinic,
  • Clinic, hospital, medicine, treatment, patient,
  • Patient, waiting, illness, recovery, care,
  • Care, nurture, support, help, kindness,
  • Kindness, compassion, empathy, generosity, altruism,
  • Altruism, selflessness, charity, donation, volunteer,
  • Volunteer, community, service, contribution, impact


Let's do that again, except the first starting word is Phoenix this time. Let's see what you come up with differently this time.
Certainly, I'll start the word game with "Phoenix" and continue for 25 repetitions:
  1. Phoenix, rebirth, fire, mythology, Arizona,
  2. Arizona, desert, cactus, heat, Grand Canyon,
  3. Grand Canyon, Colorado River, erosion, geology, tourism,
  4. Tourism, travel, vacation, sightseeing, passport,
  5. Passport, identity, citizenship, border, international,
  6. International, global, world, culture, diplomacy,
  7. Diplomacy, negotiation, politics, ambassador, treaty,
  8. Treaty, agreement, contract, signature, alliance,
  9. Alliance, partnership, cooperation, team, collaboration,
  10. Collaboration, project, work, creativity, innovation,
  11. Innovation, technology, invention, progress, future,
  12. Future, time, prediction, science fiction, possibilities,
  13. Possibilities, options, choices, decisions, opportunity,
  14. Opportunity, chance, luck, fortune, serendipity,
  15. Serendipity, coincidence, unexpected, discovery, surprise,
  16. Surprise, shock, astonishment, revelation, gift,
  17. Gift, present, generosity, occasion, wrapping,
  18. Wrapping, paper, packaging, protection, concealment,
  19. Concealment, hiding, secrecy, mystery, detection,
  20. Detection, investigation, clue, detective, puzzle,
  21. Puzzle, game, challenge, solution, strategy,
  22. Strategy, plan, tactics, goal, implementation,
  23. Implementation, execution, action, process, result,
  24. Result, outcome, consequence, effect, conclusion,
  25. Conclusion, end, finale, summary, resolution
This version of the word game, starting with "Phoenix," demonstrates how different initial words can lead to unique chains of associations. The game touches on various themes including mythology, geography, politics, innovation, and more. Would you like me to explain any of the word connections or continue the game further?
 

Tuco

I got Tuco'd!
<Gold Donor>
47,812
82,235
I made a game with Sonnet 3.5 that if you guys want to try out and play.

You enter a word, the word is flashed with the corresponding numbers associated with the letters, you then select an above prediction (lowest number you guess it is) and after that select a below prediction (highest number you guess it is) and then finally select what you estimated or predict the word sum value is, between the highlighted cells for the above and below prediction.

Word Sum Prediction Game

I suggest playing it on phone but you can play from PC.

It's a game I've had on my mind for +4 years, just never knew how to code. Finally I can make it with GPT.
Fun game, but I don't quite understand how the word sum value is tabulated. The word "And" produced a 1, 4 and 14, summing to 19. How did it come up with those three numbers?
 

Lolkaitis

Golden Squire
19
7
Fun game, but I don't quite understand how the word sum value is tabulated. The word "And" produced a 1, 4 and 14, summing to 19. How did it come up with those three numbers?

It takes the alphabet and numbers it a-z which is 1-26. The colored number range option allows you to estimate the total word sum a lil bit better but I find it harder to remember the numbers to form a word sum prediction with different colored numbers. I suggest using the "Use Prediction Window" because that allows you to get flashed the word, absorb the numbers, quickly take those numbers you see and estimate the total sum of them, then you select the total word sum on the grid. Instead of choosing an above prediction and below prediction number first. I think doing those are distracting from you calculating your first guess at total word sum from initial flash.
 
  • 1Like
Reactions: 1 user

Tuco

I got Tuco'd!
<Gold Donor>
47,812
82,235
It takes the alphabet and numbers it a-z which is 1-26. The colored number range option allows you to estimate the total word sum a lil bit better but I find it harder to remember the numbers to form a word sum prediction with different colored numbers. I suggest using the "Use Prediction Window" because that allows you to get flashed the word, absorb the numbers, quickly take those numbers you see and estimate the total sum of them, then you select the total word sum on the grid. Instead of choosing an above prediction and below prediction number first. I think doing those are distracting from you calculating your first guess at total word sum from initial flash.
ah ok, I was conflating it with your other post about word association. Pretty cool!
 

Lolkaitis

Golden Squire
19
7
I definitely recommend using this prompt for some word association fun. I definitely think this is good for the brain.

I want you to list 4 words off that could be related to the 1 word, so 5 words that relate to the 1st used word. Then I want you to take the 5th word that is listed and list 4 words that relate to it. I want you to rinse repeat this 10 times. I want all the words to be separated by comma and a space, followed by next word with a comma after it and a space again. I want to see how you are good with generating this word game with your LLM capabilities. Do this 25 times. Start with the word "_your_word_here_"