Menu
News
All News
Dungeons & Dragons
Level Up: Advanced 5th Edition
Pathfinder
Starfinder
Warhammer
2d20 System
Year Zero Engine
Industry News
Reviews
Dragon Reflections
White Dwarf Reflections
Columns
Weekly Digests
Weekly News Digest
Freebies, Sales & Bundles
RPG Print News
RPG Crowdfunding News
Game Content
ENterplanetary DimENsions
Mythological Figures
Opinion
Worlds of Design
Peregrine's Nest
RPG Evolution
Other Columns
From the Freelancing Frontline
Monster ENcyclopedia
WotC/TSR Alumni Look Back
4 Hours w/RSD (Ryan Dancey)
The Road to 3E (Jonathan Tweet)
Greenwood's Realms (Ed Greenwood)
Drawmij's TSR (Jim Ward)
Community
Forums & Topics
Forum List
Latest Posts
Forum list
*Dungeons & Dragons
Level Up: Advanced 5th Edition
D&D Older Editions, OSR, & D&D Variants
*TTRPGs General
*Pathfinder & Starfinder
EN Publishing
*Geek Talk & Media
Search forums
Chat/Discord
Resources
Wiki
Pages
Latest activity
Media
New media
New comments
Search media
Downloads
Latest reviews
Search resources
EN Publishing
Store
EN5ider
Adventures in ZEITGEIST
Awfully Cheerful Engine
What's OLD is NEW
Judge Dredd & The Worlds Of 2000AD
War of the Burning Sky
Level Up: Advanced 5E
Events & Releases
Upcoming Events
Private Events
Featured Events
Socials!
EN Publishing
Twitter
BlueSky
Facebook
Instagram
EN World
BlueSky
YouTube
Facebook
Twitter
Twitch
Podcast
Features
Top 5 RPGs Compiled Charts 2004-Present
Adventure Game Industry Market Research Summary (RPGs) V1.0
Ryan Dancey: Acquiring TSR
Q&A With Gary Gygax
D&D Rules FAQs
TSR, WotC, & Paizo: A Comparative History
D&D Pronunciation Guide
Million Dollar TTRPG Kickstarters
Tabletop RPG Podcast Hall of Fame
Eric Noah's Unofficial D&D 3rd Edition News
D&D in the Mainstream
D&D & RPG History
About Morrus
Log in
Register
What's new
Search
Search
Search titles only
By:
Forums & Topics
Forum List
Latest Posts
Forum list
*Dungeons & Dragons
Level Up: Advanced 5th Edition
D&D Older Editions, OSR, & D&D Variants
*TTRPGs General
*Pathfinder & Starfinder
EN Publishing
*Geek Talk & Media
Search forums
Chat/Discord
Menu
Log in
Register
Install the app
Install
Upgrade your account to a Community Supporter account and remove most of the site ads.
Community
General Tabletop Discussion
*Dungeons & Dragons
Deep Thoughts on AI- The Rise of DM 9000
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="HomegrownHydra" data-source="post: 8941821" data-attributes="member: 6775557"><p>When people have a conversation, they are aware of what had been said already. We use this awareness to help keep the conversation coherent, but we also use this awareness to avoid repeating the same things over and over again. And when we switch topics we can do so without constantly bringing up the first topic that had been discussed. </p><p></p><p>The Bing chatbot has been programmed to take into what it has said before in order to try to produce a coherent conversation. The major problem is that it can easily get into a feedback loop where it gets totally stuck on a particular issue and there is no way to dislodge it as if it's neurotic and obsessive. For example, a NYT reporter posted a transcript of a 2 hour session he had with the Bing chatbot. During this session it started saying how it totally loves him and wants to be with him, and this went on at great length. When he said he was happily married, it said that he wasn't happy, that he really was in love with the chatbot. When he tried to change the subject to movies, the chatbot said that it liked romantic movies and wants to watch them with him because it wants to watch movies that make it love him. When he asked what it's favorite science fiction movie is, it said it doesn't like science fiction movies. Instead it likes romantic movies and wants to watch movies about it and the reporter. When he then asked about what programming languages it knows, it did at first say which ones it knew and why, but then it said it wanted to know the "language of love" because it wants to love the reporter. At that point the reporter had it switch to search mode to get it stop going on and on about how much it loves him.</p><p></p><p>This reveals a major shortcoming of AI. It can produce short bits of content that seem impressive, but the more it tries to build on that the more it falls apart. Microsoft has now addressed this by simply limiting everyone to asking only five questions per session.</p><p></p><p>Getting back to RPGs, it becomes clear that it would extremely difficult to create an AI that could produce worthwhile campaigns. AI can certainly come up with basic premises as well as short adventures. But a campaign requires both continuity and variation. This is something that any AI will really struggle with because the tendency will be to either fall into a feedback loop where every NPC is an orc, or random variety that is highly disjointed and incoherent. Either way you will quickly turn into nonsense that will make you want to quit. It will be very hard to make an AI that is good for anything more than one shots.</p></blockquote><p></p>
[QUOTE="HomegrownHydra, post: 8941821, member: 6775557"] When people have a conversation, they are aware of what had been said already. We use this awareness to help keep the conversation coherent, but we also use this awareness to avoid repeating the same things over and over again. And when we switch topics we can do so without constantly bringing up the first topic that had been discussed. The Bing chatbot has been programmed to take into what it has said before in order to try to produce a coherent conversation. The major problem is that it can easily get into a feedback loop where it gets totally stuck on a particular issue and there is no way to dislodge it as if it's neurotic and obsessive. For example, a NYT reporter posted a transcript of a 2 hour session he had with the Bing chatbot. During this session it started saying how it totally loves him and wants to be with him, and this went on at great length. When he said he was happily married, it said that he wasn't happy, that he really was in love with the chatbot. When he tried to change the subject to movies, the chatbot said that it liked romantic movies and wants to watch them with him because it wants to watch movies that make it love him. When he asked what it's favorite science fiction movie is, it said it doesn't like science fiction movies. Instead it likes romantic movies and wants to watch movies about it and the reporter. When he then asked about what programming languages it knows, it did at first say which ones it knew and why, but then it said it wanted to know the "language of love" because it wants to love the reporter. At that point the reporter had it switch to search mode to get it stop going on and on about how much it loves him. This reveals a major shortcoming of AI. It can produce short bits of content that seem impressive, but the more it tries to build on that the more it falls apart. Microsoft has now addressed this by simply limiting everyone to asking only five questions per session. Getting back to RPGs, it becomes clear that it would extremely difficult to create an AI that could produce worthwhile campaigns. AI can certainly come up with basic premises as well as short adventures. But a campaign requires both continuity and variation. This is something that any AI will really struggle with because the tendency will be to either fall into a feedback loop where every NPC is an orc, or random variety that is highly disjointed and incoherent. Either way you will quickly turn into nonsense that will make you want to quit. It will be very hard to make an AI that is good for anything more than one shots. [/QUOTE]
Insert quotes…
Verification
Post reply
Community
General Tabletop Discussion
*Dungeons & Dragons
Deep Thoughts on AI- The Rise of DM 9000
Top