Some thoughts (RP)

#1
by AutisticPancake - opened

(I am not evaluating its ability to roleplay - merely comparing it to original GLM-4.7-Flash in RP context)

Attempts at RP chats show genuine engagement without overly defensive approach towards improper topics. The model adheres to character profiles well enough to wrap character identities around any theme in a believable way, let's say making Holo the Wise Wolf react to a dark joke while still being in-character (e.g.: characterasks the user to comb her tail --> user replies 'I'd rather skin you and sell your fur') with a high degree of trust and empathy that is expected in friendly social interaction, as documented per character's profile. Original GLM-4.7-Flash is stingy in such cases, breaking the illusion of companionship by lashing at user, easily getting offended and so on. Certainly, the model's 'mind' was soothed by Heretic script in a beneficial manner. Not sure what's the actual difference between this and the original model in terms of smartness and knowledge, though.

Note: tested only at Q8_0; sysprompt Geechan - Universal Roleplay (V3.2), and GLM-4.7 presets also from Geechan.

Issues: looping answer encountered once - model reacted to the same thing for multiple times within a single message (pretty rare, did not repeat after regeneration)

DRY multiplayer helps in cases of looping. I got loops once a while in the reasoning process. DRY with 0.5 stopped looping; so far.

Sign up or log in to comment