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
*TTRPGs General
How well can a dedicated RPG GenAI perform?
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="Gorgon Zee" data-source="post: 9457192" data-attributes="member: 75787"><p>Right. The danger is when you ask for a fact that does not exist. As an example, if I ask Chat-GPT for a table of animals and famous stuffed toys based on them, I get this:</p><ul> <li data-xf-list-type="ul"><strong>Bear</strong>: Teddy Bear (Named after President Theodore Roosevelt)</li> <li data-xf-list-type="ul"><strong>Elephant</strong>: Babar (From the children's book series "Babar the Elephant")</li> <li data-xf-list-type="ul"><strong>Rabbit</strong>: Peter Rabbit (From Beatrix Potter's stories)</li> <li data-xf-list-type="ul"><strong>Dog</strong>: Snoopy (From the "Peanuts" comic strip by Charles M. Schulz)</li> <li data-xf-list-type="ul"><strong>Cat</strong>: Hello Kitty (From Sanrio, a popular Japanese character)</li> <li data-xf-list-type="ul"><strong>Kangaroo</strong>: Kanga and Roo (From A.A. Milne's "Winnie-the-Pooh")</li> <li data-xf-list-type="ul"><strong>Monkey</strong>: Curious George (From the children's book series "Curious George")</li> <li data-xf-list-type="ul"><strong>Pig</strong>: Piglet (From A.A. Milne's "Winnie-the-Pooh")</li> <li data-xf-list-type="ul"><strong>Duck</strong>: Donald Duck (From Disney's famous character)</li> <li data-xf-list-type="ul"><strong>Tiger</strong>: Tigger (From A.A. Milne's "Winnie-the-Pooh")</li> </ul><p>When I then ask it to add Rhinocerous to this list, it adds this:</p><ul> <li data-xf-list-type="ul"><strong>Rhinoceros</strong>: Moominmamma (Though the Moomins are actually a type of troll, their appearance is often likened to a hippopotamus or rhinoceros-like creature;</li> </ul><p>Now calling a moomin based on a rhinocerous is a bit of a stretch -- I'd classify that as an error. The LLM did actually qualify its results, which is nice, but we might have been unlucky and not have had it done so.</p><p></p><p>The problem is that it has this compelling pattern of names and toys and the pattern-matching agent really wants to keep that going. You have to give it instructions on what to do on a failure to keep it from fabricating: If I try the query <em>add another animal to the original list of 10 , a rhinocerous. But if you cannot find a suitable stuffed toy, do not guess but instead say "I cannot find a toy"</em>, the it adds this instead:</p><ul> <li data-xf-list-type="ul"><strong>Rhinoceros</strong>: I cannot find a famous stuffed toy based on a rhinoceros.</li> </ul><p>In many ways, designing good prompts is like working out the personality of someone and craftily phrasing things to bring out the best in them and let them fail graciously.</p></blockquote><p></p>
[QUOTE="Gorgon Zee, post: 9457192, member: 75787"] Right. The danger is when you ask for a fact that does not exist. As an example, if I ask Chat-GPT for a table of animals and famous stuffed toys based on them, I get this: [LIST] [*][B]Bear[/B]: Teddy Bear (Named after President Theodore Roosevelt) [*][B]Elephant[/B]: Babar (From the children's book series "Babar the Elephant") [*][B]Rabbit[/B]: Peter Rabbit (From Beatrix Potter's stories) [*][B]Dog[/B]: Snoopy (From the "Peanuts" comic strip by Charles M. Schulz) [*][B]Cat[/B]: Hello Kitty (From Sanrio, a popular Japanese character) [*][B]Kangaroo[/B]: Kanga and Roo (From A.A. Milne's "Winnie-the-Pooh") [*][B]Monkey[/B]: Curious George (From the children's book series "Curious George") [*][B]Pig[/B]: Piglet (From A.A. Milne's "Winnie-the-Pooh") [*][B]Duck[/B]: Donald Duck (From Disney's famous character) [*][B]Tiger[/B]: Tigger (From A.A. Milne's "Winnie-the-Pooh") [/LIST] When I then ask it to add Rhinocerous to this list, it adds this: [LIST] [*][B]Rhinoceros[/B]: Moominmamma (Though the Moomins are actually a type of troll, their appearance is often likened to a hippopotamus or rhinoceros-like creature; [/LIST] Now calling a moomin based on a rhinocerous is a bit of a stretch -- I'd classify that as an error. The LLM did actually qualify its results, which is nice, but we might have been unlucky and not have had it done so. The problem is that it has this compelling pattern of names and toys and the pattern-matching agent really wants to keep that going. You have to give it instructions on what to do on a failure to keep it from fabricating: If I try the query [I]add another animal to the original list of 10 , a rhinocerous. But if you cannot find a suitable stuffed toy, do not guess but instead say "I cannot find a toy"[/I], the it adds this instead: [LIST] [*][B]Rhinoceros[/B]: I cannot find a famous stuffed toy based on a rhinoceros. [/LIST] In many ways, designing good prompts is like working out the personality of someone and craftily phrasing things to bring out the best in them and let them fail graciously. [/QUOTE]
Insert quotes…
Verification
Post reply
Community
General Tabletop Discussion
*TTRPGs General
How well can a dedicated RPG GenAI perform?
Top
