home.social

#aidungeon — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #aidungeon, aggregated by home.social.

  1. 🔧 Create immersive game mechanics with #TogetherAI & #AIDungeon, including inventory systems and state tracking

    🛡️ Implement content safety using #LlamaGuard and custom policies

    💻 Develop user interface with #Gradio for a complete gaming experience

  2. 🔧 Create immersive game mechanics with #TogetherAI & #AIDungeon, including inventory systems and state tracking

    🛡️ Implement content safety using #LlamaGuard and custom policies

    💻 Develop user interface with #Gradio for a complete gaming experience

  3. 🔧 Create immersive game mechanics with #TogetherAI & #AIDungeon, including inventory systems and state tracking

    🛡️ Implement content safety using #LlamaGuard and custom policies

    💻 Develop user interface with #Gradio for a complete gaming experience

  4. 🔧 Create immersive game mechanics with #TogetherAI & #AIDungeon, including inventory systems and state tracking

    🛡️ Implement content safety using #LlamaGuard and custom policies

    💻 Develop user interface with #Gradio for a complete gaming experience

  5. 🔧 Create immersive game mechanics with #TogetherAI & #AIDungeon, including inventory systems and state tracking

    🛡️ Implement content safety using #LlamaGuard and custom policies

    💻 Develop user interface with #Gradio for a complete gaming experience

  6. Even #AIDungeon has politics on the brain right now...

    (Also, surprised at how much the newer models pick up from the old #Modders scenario: I said I was Frankie and it pulled Dale and the ConSoc stuff unprompted.)

  7. Even #AIDungeon has politics on the brain right now...

    (Also, surprised at how much the newer models pick up from the old #Modders scenario: I said I was Frankie and it pulled Dale and the ConSoc stuff unprompted.)

  8. Even #AIDungeon has politics on the brain right now...

    (Also, surprised at how much the newer models pick up from the old #Modders scenario: I said I was Frankie and it pulled Dale and the ConSoc stuff unprompted.)

  9. Even #AIDungeon has politics on the brain right now...

    (Also, surprised at how much the newer models pick up from the old #Modders scenario: I said I was Frankie and it pulled Dale and the ConSoc stuff unprompted.)

  10. Even #AIDungeon has politics on the brain right now...

    (Also, surprised at how much the newer models pick up from the old #Modders scenario: I said I was Frankie and it pulled Dale and the ConSoc stuff unprompted.)

  11. The best part about #AIDungeon is that you can just take of your clothes in any situation, and all the NPCs will just go along with it if you tell them to take off their clothes too.

    What other text-based roleplaying game lets you just be naked?

  12. The best part about #AIDungeon is that you can just take of your clothes in any situation, and all the NPCs will just go along with it if you tell them to take off their clothes too.

    What other text-based roleplaying game lets you just be naked?

  13. The best part about #AIDungeon is that you can just take of your clothes in any situation, and all the NPCs will just go along with it if you tell them to take off their clothes too.

    What other text-based roleplaying game lets you just be naked?

  14. The best part about #AIDungeon is that you can just take of your clothes in any situation, and all the NPCs will just go along with it if you tell them to take off their clothes too.

    What other text-based roleplaying game lets you just be naked?

  15. The best part about #AIDungeon is that you can just take of your clothes in any situation, and all the NPCs will just go along with it if you tell them to take off their clothes too.

    What other text-based roleplaying game lets you just be naked?

  16. @jhulten @darkuncle @skorgu
    I felt #AIDungeon had a good use case: it doesn't try to give you true facts, it just writes a story with you, like a text-based roleplaying game. That, and summarizers and analyzers, if you don't assume they're always going to be correct, seem to be use-cases AI is ready for.

  17. @jhulten @darkuncle @skorgu
    I felt #AIDungeon had a good use case: it doesn't try to give you true facts, it just writes a story with you, like a text-based roleplaying game. That, and summarizers and analyzers, if you don't assume they're always going to be correct, seem to be use-cases AI is ready for.

  18. @jhulten @darkuncle @skorgu
    I felt #AIDungeon had a good use case: it doesn't try to give you true facts, it just writes a story with you, like a text-based roleplaying game. That, and summarizers and analyzers, if you don't assume they're always going to be correct, seem to be use-cases AI is ready for.

  19. @jhulten @darkuncle @skorgu
    I felt #AIDungeon had a good use case: it doesn't try to give you true facts, it just writes a story with you, like a text-based roleplaying game. That, and summarizers and analyzers, if you don't assume they're always going to be correct, seem to be use-cases AI is ready for.

  20. @jhulten @darkuncle @skorgu
    I felt had a good use case: it doesn't try to give you true facts, it just writes a story with you, like a text-based roleplaying game. That, and summarizers and analyzers, if you don't assume they're always going to be correct, seem to be use-cases AI is ready for.

  21. @parismarx
    So #Latitude was experimenting with stuff like this back in 2020 with #AIDungeon. I don't remember the details, but I remember they had a feature at some point that would have an AI try to summarize the story from before where the story-generating AI could see. They moved back to just having the player manually enter it at some point, but that shows that this technology isn't new, and has been deemed to not be worth it in the past.

    The main issues I can see here are that having an AI analyze a ton of input and generate a textual summary creates a lot more room for hallucination: it doesn't know what any of this means, so it doesn't know what's actually important, or even how to lay that out in such a way that the main AI, ChatGPT, isn't going to have its own hallucinations from it.

    I can definitely see it picking up that a user wants to be lied to, and telling GPT to lie. I can also see executives selling / using this AI generated user-info as if it's reliable.

  22. @parismarx
    So #Latitude was experimenting with stuff like this back in 2020 with #AIDungeon. I don't remember the details, but I remember they had a feature at some point that would have an AI try to summarize the story from before where the story-generating AI could see. They moved back to just having the player manually enter it at some point, but that shows that this technology isn't new, and has been deemed to not be worth it in the past.

    The main issues I can see here are that having an AI analyze a ton of input and generate a textual summary creates a lot more room for hallucination: it doesn't know what any of this means, so it doesn't know what's actually important, or even how to lay that out in such a way that the main AI, ChatGPT, isn't going to have its own hallucinations from it.

    I can definitely see it picking up that a user wants to be lied to, and telling GPT to lie. I can also see executives selling / using this AI generated user-info as if it's reliable.

  23. @parismarx
    So #Latitude was experimenting with stuff like this back in 2020 with #AIDungeon. I don't remember the details, but I remember they had a feature at some point that would have an AI try to summarize the story from before where the story-generating AI could see. They moved back to just having the player manually enter it at some point, but that shows that this technology isn't new, and has been deemed to not be worth it in the past.

    The main issues I can see here are that having an AI analyze a ton of input and generate a textual summary creates a lot more room for hallucination: it doesn't know what any of this means, so it doesn't know what's actually important, or even how to lay that out in such a way that the main AI, ChatGPT, isn't going to have its own hallucinations from it.

    I can definitely see it picking up that a user wants to be lied to, and telling GPT to lie. I can also see executives selling / using this AI generated user-info as if it's reliable.

  24. @parismarx
    So #Latitude was experimenting with stuff like this back in 2020 with #AIDungeon. I don't remember the details, but I remember they had a feature at some point that would have an AI try to summarize the story from before where the story-generating AI could see. They moved back to just having the player manually enter it at some point, but that shows that this technology isn't new, and has been deemed to not be worth it in the past.

    The main issues I can see here are that having an AI analyze a ton of input and generate a textual summary creates a lot more room for hallucination: it doesn't know what any of this means, so it doesn't know what's actually important, or even how to lay that out in such a way that the main AI, ChatGPT, isn't going to have its own hallucinations from it.

    I can definitely see it picking up that a user wants to be lied to, and telling GPT to lie. I can also see executives selling / using this AI generated user-info as if it's reliable.

  25. @parismarx
    So was experimenting with stuff like this back in 2020 with . I don't remember the details, but I remember they had a feature at some point that would have an AI try to summarize the story from before where the story-generating AI could see. They moved back to just having the player manually enter it at some point, but that shows that this technology isn't new, and has been deemed to not be worth it in the past.

    The main issues I can see here are that having an AI analyze a ton of input and generate a textual summary creates a lot more room for hallucination: it doesn't know what any of this means, so it doesn't know what's actually important, or even how to lay that out in such a way that the main AI, ChatGPT, isn't going to have its own hallucinations from it.

    I can definitely see it picking up that a user wants to be lied to, and telling GPT to lie. I can also see executives selling / using this AI generated user-info as if it's reliable.

  26. AI Dungeon: Artificial intelligence turns Gamemaster, creating infinite worlds to adventure in - Let’s get this out of the way first, AI Dungeon is not a new game, but it is updat... - readwrite.com/ai-dungeon-artif #aidungeon #aigaming #game #news #ai

  27. AI Dungeon: Artificial intelligence turns Gamemaster, creating infinite worlds to adventure in - Let’s get this out of the way first, AI Dungeon is not a new game, but it is updat... - readwrite.com/ai-dungeon-artif #aidungeon #aigaming #game #news #ai

  28. AI Dungeon: Artificial intelligence turns Gamemaster, creating infinite worlds to adventure in - Let’s get this out of the way first, AI Dungeon is not a new game, but it is updat... - readwrite.com/ai-dungeon-artif #aidungeon #aigaming #game #news #ai

  29. AI Dungeon: Artificial intelligence turns Gamemaster, creating infinite worlds to adventure in - Let’s get this out of the way first, AI Dungeon is not a new game, but it is updat... - readwrite.com/ai-dungeon-artif #aidungeon #aigaming #game #news #ai

  30. AI Dungeon: Artificial intelligence turns Gamemaster, creating infinite worlds to adventure in - Let’s get this out of the way first, AI Dungeon is not a new game, but it is updat... - readwrite.com/ai-dungeon-artif #aidungeon #aigaming #game #news #ai

  31. @thomasfuchs
    #Resonite is impressing me lately with just how open content development can be in an open virtual space, giving me great hope for #VR as a medium finally moving into maturity.

    Same with #Fediverse / #ActivityPub / #Mastodon. Very happy with watching a communalization project slowly take over a mature, undifferentiated market.

    Also very happy with some of the stuff that was coming out of the computer chips community before the pandemic, as RTX is an underrated achievement, on top of our ability to run massive systems like AI through CUDA.

    And speaking of AI, look into #AIDungeon by #Latitude: having it write tandem stories with the user is exactly the kind of thing the current technology is suited for.

  32. @thomasfuchs
    #Resonite is impressing me lately with just how open content development can be in an open virtual space, giving me great hope for #VR as a medium finally moving into maturity.

    Same with #Fediverse / #ActivityPub / #Mastodon. Very happy with watching a communalization project slowly take over a mature, undifferentiated market.

    Also very happy with some of the stuff that was coming out of the computer chips community before the pandemic, as RTX is an underrated achievement, on top of our ability to run massive systems like AI through CUDA.

    And speaking of AI, look into #AIDungeon by #Latitude: having it write tandem stories with the user is exactly the kind of thing the current technology is suited for.

  33. @thomasfuchs
    #Resonite is impressing me lately with just how open content development can be in an open virtual space, giving me great hope for #VR as a medium finally moving into maturity.

    Same with #Fediverse / #ActivityPub / #Mastodon. Very happy with watching a communalization project slowly take over a mature, undifferentiated market.

    Also very happy with some of the stuff that was coming out of the computer chips community before the pandemic, as RTX is an underrated achievement, on top of our ability to run massive systems like AI through CUDA.

    And speaking of AI, look into #AIDungeon by #Latitude: having it write tandem stories with the user is exactly the kind of thing the current technology is suited for.

  34. @thomasfuchs
    #Resonite is impressing me lately with just how open content development can be in an open virtual space, giving me great hope for #VR as a medium finally moving into maturity.

    Same with #Fediverse / #ActivityPub / #Mastodon. Very happy with watching a communalization project slowly take over a mature, undifferentiated market.

    Also very happy with some of the stuff that was coming out of the computer chips community before the pandemic, as RTX is an underrated achievement, on top of our ability to run massive systems like AI through CUDA.

    And speaking of AI, look into #AIDungeon by #Latitude: having it write tandem stories with the user is exactly the kind of thing the current technology is suited for.

  35. @thomasfuchs
    is impressing me lately with just how open content development can be in an open virtual space, giving me great hope for as a medium finally moving into maturity.

    Same with / / . Very happy with watching a communalization project slowly take over a mature, undifferentiated market.

    Also very happy with some of the stuff that was coming out of the computer chips community before the pandemic, as RTX is an underrated achievement, on top of our ability to run massive systems like AI through CUDA.

    And speaking of AI, look into by : having it write tandem stories with the user is exactly the kind of thing the current technology is suited for.

  36. @emilymbender
    Not sure I'm going to get the time to absorb this whole thing today, but I still feel like #AIDungeon is the best example of an ethical use-case. They don't copyright the text, nor do they claim it will be at all truthful or even good, they just provide access to the AI in a way that people can use it as a game/storytelling tool. No one is harmed, nothing is claimed, the only thing being charged for is the interface used to interact and the hardware being used to run it.

    Also, I had no idea that was how you pronounce Dr Gebru's first name.

    Edit: I see you are saying you don't know a specific product for your LLM-powered NPC example, so have one: #AIDungeon. I'd LOVE your feedback on how ethical/sustainable you think it is!

  37. @emilymbender
    Not sure I'm going to get the time to absorb this whole thing today, but I still feel like #AIDungeon is the best example of an ethical use-case. They don't copyright the text, nor do they claim it will be at all truthful or even good, they just provide access to the AI in a way that people can use it as a game/storytelling tool. No one is harmed, nothing is claimed, the only thing being charged for is the interface used to interact and the hardware being used to run it.

    Also, I had no idea that was how you pronounce Dr Gebru's first name.

    Edit: I see you are saying you don't know a specific product for your LLM-powered NPC example, so have one: #AIDungeon. I'd LOVE your feedback on how ethical/sustainable you think it is!

  38. @emilymbender
    Not sure I'm going to get the time to absorb this whole thing today, but I still feel like #AIDungeon is the best example of an ethical use-case. They don't copyright the text, nor do they claim it will be at all truthful or even good, they just provide access to the AI in a way that people can use it as a game/storytelling tool. No one is harmed, nothing is claimed, the only thing being charged for is the interface used to interact and the hardware being used to run it.

    Also, I had no idea that was how you pronounce Dr Gebru's first name.

    Edit: I see you are saying you don't know a specific product for your LLM-powered NPC example, so have one: #AIDungeon. I'd LOVE your feedback on how ethical/sustainable you think it is!

  39. @emilymbender
    Not sure I'm going to get the time to absorb this whole thing today, but I still feel like #AIDungeon is the best example of an ethical use-case. They don't copyright the text, nor do they claim it will be at all truthful or even good, they just provide access to the AI in a way that people can use it as a game/storytelling tool. No one is harmed, nothing is claimed, the only thing being charged for is the interface used to interact and the hardware being used to run it.

    Also, I had no idea that was how you pronounce Dr Gebru's first name.

    Edit: I see you are saying you don't know a specific product for your LLM-powered NPC example, so have one: #AIDungeon. I'd LOVE your feedback on how ethical/sustainable you think it is!

  40. @emilymbender
    Not sure I'm going to get the time to absorb this whole thing today, but I still feel like is the best example of an ethical use-case. They don't copyright the text, nor do they claim it will be at all truthful or even good, they just provide access to the AI in a way that people can use it as a game/storytelling tool. No one is harmed, nothing is claimed, the only thing being charged for is the interface used to interact and the hardware being used to run it.

    Also, I had no idea that was how you pronounce Dr Gebru's first name.

    Edit: I see you are saying you don't know a specific product for your LLM-powered NPC example, so have one: . I'd LOVE your feedback on how ethical/sustainable you think it is!

  41. @slashdot
    But I already did that in #AIDungeon. We already know that works, you just feed it some quotes and it starts trying to emulate them... And then it says something insane.

    Are they going to make Abraham Lincoln say insane things now?