Update README.md

README.md

@@ -11,6 +11,8 @@ base_model:
 
 hasnonname's trashpanda baby is getting a sequel. More JLLM-ish than ever, too.
 
+"You can take the user out of JanitorAI but you can't take the JLLM out of them." - OwenArli, 2025
+
 <p><b>Severian's notes</b>: No longer as unhinged as v0, so we're discontinuing the instruct version. Varied rerolls, good character/scenario handling, almost no user impersonation now. Huge dependence on intro message quality, but lets it follow up messages from larger models quite nicely. Currently considering it as an overall improvement over v0 as far as tester feedback is concerned. Still seeing some slop and an occasional bad reroll response, though.</p>
 
 <p>Let us know what you think, if it did well we'll spread it to other base models.</p>
@@ -65,6 +67,10 @@ Big thanks to the folks in the trashpanda-org discord for testing and sending ov
 
 — moothdragon
 
+> I’m totally into Mullein V1’s language—it’s just so good. It’s like it has all the best parts of JLLM without most of the downsides. [...] barely ever tries to impersonate the user, which is pretty nice. It’s my default model for roleplaying now.
+
+— Silver
+
 
 ## Just us having fun, don't mind it