@rayon's banner p

rayon

waifutech enthusiast

2 followers   follows 1 user  
joined 2023 August 17 08:48:30 UTC

The Dork Enlightenment


				
User ID: 2632


				
				
				

			

		

	














	


		


			



	

		

			

			

				

					

						

							
						

						

							
							

								
rayon


								

								

								
								
								

								
							
					
 
				


				
waifutech enthusiast

				
				
				

				

					2 followers  

					follows 1 user  

					joined 2023 August 17 08:48:30 UTC
				


				
					

					
The Dork Enlightenment



				

				

				

				

				

					

					

					
					
					

					
User ID: 2632


					
					
					
				

			


					

						
					



		

	

 











			
			

			
			

			




	


		

			
‎

			

				
				

					Hour
					Day
					Week
					
					Year
					All
				

			


			
‎

			

	
	

	 Hot Bump Top Bottom Old Controversial Comments
	



		

	






	

		
		

		
		
	

	

  







		

			
			
				Small-Scale Question Sunday for August 16, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
I suppose I can always shill SillyTavern again, which despite a barely-responsive dev is still the most feature-complete LLM frontend I've tried; out of home for the week, I'm currently forced to use Agnaistic and I stumble over UI knobs and switches too often to be able to goon at all.


I don't have the Tavern UI before me but off the top of my head:




lets me write the overall style guide,




The prompts settings let you set the exact content and order of the entire wall of text you send to the LLM.




character / setting notes,




Main body of character notes goes into card definitions, setting can go into the additional info -> scenario field. It's sent as text anyway so this is more of a convenience thing.




"previously on Buffy the Vampire Slayer in the last chapter" condensed history notes




goes into Author's Note, optionally buried on some # message depth in the chat history; I usually just put PAST EVENTS (separated with newlines etc.) after char defs.




and then the notes for the scene (and the beginning of the next scene to help flow). The scene notes would be a combination of "A does X, B mentions Y" and occasional inserted sentences like "The silence was interrupted by a doorbell ring" (that are more ideas for the LLM and don't need to be preserved as-is).




If you don't want to actually self-insert chat, you can just put instructions in your "replies" as long as your prompt sequence/preset says that this can be a possibility. Usually LLMs are smart enough that I can just "say" something like [OOC: now draw describe her getting an education] and get the needed continuation.




It should let me generate multiple variations, manually edit the previous prompts and generated results for continuation and crucially never delete unused generations so I can later steal sentences and ideas from them (but I don't need explicit branching from every response).




All in by default, in fact I think "swipes" and generally complete control over chats is the comfiest feature of ST by far and I have no idea why this is not the default in corpo apps. I tried the Claude app for work after years of chatbotting and I frequently raged at the stupid frontend preventing me from editing old responses or forking chats for no reason far as I can see. Cursor feels much better in this regard.


Your call on how usable ST's UI is, it's fairly customizable and I've grown to like it against my will anyway.


I'll echo other posters and caveat that my own experience with genning OC things based on my own drafts has been mostly disappointing (too prone to getting stuck on character quirks and needing to show them off in some fashion in every fucking response), but I'm not the karma police here. Might be a prompt issue on my part.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Small-Scale Question Sunday for August 16, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
Sitting down on your own shitter in your own bathroom after a multi-day work trip or a long day outside.


t. saving the game rn


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Culture War Roundup for the week of August 10, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					


Prompt injection has gone from Sci-Fi to an active concern to largely solved already.




As long as Claude (PBUH) continues to write smut for me on demand I wouldn't say prompt injection has been "solved", and I'll also note that the most impactful way they've found to actually counteract prompt injection was to just flatly shut off prefilling capability for newer versions of Claude. In my view that is an admission of defeat, and a skill issue that Anthropic has not found a way to meaningfully circumvent, so they just took their ball and went home.


Credit where credit is due, in my experience Fable is more resistant to the usual things (especially twitchy around noncon/age gaps, refusing even SFW scenarios for fear of hurting a fictional character's feelings), actually seeing refusals again after two clean years was quite disheartening in an "ah shit, here we go again" kind of way. But even so I freely admit I've gotten rusty and complacent and haven't changed out my prompts or visited the usual suspects in like a year, and I'm pretty confident that if I'd gotten around to updating my proverbial attack trajectory (and burned some credits for testing) I could still wrest my doujin-tier slop from its cold hands. Which I really should get around to honestly, 4.x versions won't remain up forever, but I feel too pacified and in any case am mostly converted to stanning Deepseek which has none of the problems.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for July 24, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
No idea, there are public community servers but I haven't tried them, and (as lamented above) nobody in my friend circle was interested. I played the entire game in singleplayer and enjoyed it very much. Considering this is at its core a survcrafting game, co-op is probably more enjoyable and there's even raid content (of sorts) for it, but PvP is likely a more jank/mixed bag.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					


Probably the way he rephrased everything we said back at us in the interview, and then asked for confirmation.






Or the glazing and "You're right, I'll fix that" whenever there was a mistake. Apparently that's called a "Sycophantic Opener"




Also commonly known as "middle management"


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
I've heard Fields of Mistria being referred to as "Stardew Valley but gay", which confuses me given that Stardew already doesn't lack for such options. Cute waifus seem present too. Is it just the overall aesthetic?


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
Don't think those can get lower at this point but sure, I'll count my blessings. Back when chub was still usable, I remember having seen a fork of one of my publicly posted cards, with only one difference - a very bobs-and-vagene-coded sentence added to its definitions and greeting message (from the user's point of view too, not the character's like the founding fathers intended!). Granted I have zero pretensions to poetic genius here, the card was like 600 tokens of simple descriptions, but the preferences and literacy of the average coomer have since become painfully clear. In that moment Rayon was enlightened.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					


If you continue to disagree with my approach, then I am happy to accept your "silent sigh and scroll".




A flattering type of audience to strive for, surely.




It's the end of the world, I will use every tool at my disposal till it makes me obsolete.




Less charitably, my point is that contra your response to Bartender, you evidently don't see any objections as helpful; you are committed to not noticing the problem and dismissing nooticers, in whatever form - Bartender's clipped remark and my more detailed objection get the same dismissive response, in spirit if not in word count. Hence, it's hardly surprising that slop alerts from poasters continue until morale improves quality control returns.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					
I've recently been nooticing that something is definitely very weird with naming stuff in LLM-generated smut text. I'm usually a purveyor of uh, established can(n)ons so that usually helps corral the models into a more coherent mold, but recently I've been cautiously trying OC stuff based on old draftsand the naming "schemas" really stick out.


I don't know how to put it in proper words, but it feels like without a defined frame of reference ("you are {{char}} from {{vidya}}, &c"), there are certain "clustered" defaults that models resort to, based on which rough genre/setting the LLM mentally sorts your scenario into. My prompts are detailed enough that I don't get super generic stuff like my good ol friend Elara on a trek to the Whispering Woods shudder anymore, I'm not talking about those (though the existence of such certified hood classics independently encountered by so many people is in itself quite interesting), but the "mental models" the LLMs seem to keep are still quite noticeable in generic/open-ended OC scenarios - to the point that when bringing up say an as-yet-unnamed nearby town (with only the general setting and maybe name of the current one to go off of), the model's response will declare exactly the same %town_name% across several regens, despite being vaguely prompted and ostensibly taking a fresh crack at the worldbuilding every time. I have yet to test if those differ across LLMs, likely they do. Hopefully someone smarter than me is looking into it, or at least has nooticed.


				

				

						

							

								
							

						


						
					

				
			


			
			
			
				

			
		

	






		

			
			
				Friday Fun Thread for August 7, 2026
			
		

	

	

	

		
			

			

				

			

		

			


				

					


It would be helpful if the people accusing me of using too much AI would be accurate about which part (if any) is actually LLM-written or rewritten.




I believe I have been, and only got a half-hearted deflection wrt "taste" for my trouble; evidently pushback only makes your proverbial pen harder. Now I just silently sigh and scroll, if nothing else I have a lot of practice in eyeballing the general substance from walls of AI/-assisted slop writing. (Not sure if it's a perk to be proud of really, but I'd rather start preparing for the future early.)