archived

by meatrocket meatyrocket@proton.me discord: meat.rocket

| archive | presets | prompts |

---

model presets

---

sonnet v1.1 (21/06/24)

v1.1: tweaked simple v1 for new 3.5 claude model, experimental; added & tweaked md & html toggles

note: there are several toggles. i primarily enjoy my characters' thought and 1st person, so please change the main prompt & toggles as you see fit to match your context. i will work on pacing and explore better ways to rp with the model soon

outputs 2 HTML panels per reply, limiting it to 1 may improve quality of messages per reply

3.5 sonnet is a massive improvement over 3.0 sonnet. might be a tad bit dumber than opus, but it is quite proactive in roleplay, keeping it well paced while also capable of following complex instructions, as well as the speed improvement. it does tend to prefer showing & acting as well as dialogue, but specific details and descriptions probably needs improvement

sonnet v1.0a (20/06/24)

original simple v1.0 (18/06/24) v1.0a: reorganized normalmaxx & revised the entire format hotfixed prefill to adjust to prose better mid-RP theoretically, this one should be more grounded in the chat context but i don't expect much difference from normal 1.4 otherwise.

new prefill (suggested by mm & modified by me) added some nudges to better facilitate taking proper "turns" with the ai (lowering chances of assistant speaking for user) added a new hidden prompt to track NPCs in a scene

toggles: perspective (pov), writing styles (prose), dialogue (prose), mini-CoT, anti-lewd, npc tracker, user turn

inspired by euryale instruct prompts

normal v1.4 (18/06/24)

v1.4: added simple v1 nudges to better facilitate taking proper "turns" with the ai by default some prose styles are turned off, enable them at your choosing

gimmicks: HTML panels, codeblock panels, HTML text adv. prompts

normal v1.3 (19/05/24)

v1.3: a few more tweaks made to prompts, just the latest preset I have to offer

normal v1.2 (03/05/24)

v1.2: added a more jailbroken prefill

tweaked instructions a bit, experimenting with new prefill, narrator + fixed some bugs with ST extension working with the preset toggle and choose your preferred settings, some combinations may work better than others. from my own testing, i find that opus likes to talk as you only when it can't find other ways to extend (slowburn) the reply.

started from scratch, contains everything from litemaxx in a different arrangement storyteller for NPCs instead of "you are {{char}}" should work better for scenario/RPG cards

from testing, this one works well for most cards i tried i tried to slim the CoT as much as I can, try it out (usually creates more fleshed out responses from your characters) so far, it should stick to the word limit, limit lewd & generate dense content without speaking as you.

make sure to select your preferred PoV & settings

additional JBs & prompts, with word limiter

opusmaxx v1.3 (2/05/24)

v1.3: updated instructions + made retarded peanut gallery slop a separate prompt

i don't really recommend this preset anymore but i was asked to make this use this if you preferred the styles from this prompt

normal v1.1 (02/05/24)

v1.1: tweaked instructions a bit, experimenting with new prefill, narrator + fixed some bugs with ST extension working with the preset

normal v1.0 (01/05/24)

v1.0: just a normal preset

as per request, i even tried it with sonnet (without noticing i left it on) in my own slowburn and was decently impressed with the speed and content, even with the CoT included. opus is quite peculiar though so YMMV

litemaxx 1.6 (30/04/24)

v1.6: applied some tweaks to make it work for scenario cards better

i still check the thread archives, so leave your feedback (or criticisms) and ill try to improve upon it special thanks to the anons who can't be credited

lite v1.5 (28/04/24)

v1.5: fixed a bit more of the blatant issues i was seeing with the last preset; halved CoT gen. time (~32 seconds >> 15 seconds with Opus)

returned things back to inject @ 1, likely no longer need CoT to produce consistent results (at least from testing) i still recommend enabling CoT for more higher quality and consistent RPs but i would leave it off for the coom don't forget to enable the instructions you want first...

lite v1.3 (25/04/24)

v1.3: new RP instructions and CoT, tweaked all of the prompts and reduced🫃 bloat HTML prompt rewritten and improved, size decreased from 2400 tokens >> 1250 tokens

added a thinking/CoT prompt, should create cohesion between all instructions much more rigorously

RP focused preset, featuring new style toggles that are completely modular

if you want to add more prompts, insert it somewhere under jb toggles with prompt inject @ depth 0 inspired by many other anons' JBs

lite v1.0 (14/04/24)

(includes toggle for HTML/codeblock panels)

new lightweight jailbreak, using the prompting principles of my other presets as a core function. heavily reduced token usage; 900 token jb + prefill preset for Claude/GPT/Cohere/Gemini focuses heavily on the adherence to character, prose, and initiative for events

opus v1.2 (14/04/24)

v1.2: further refinements, bug fixes & massively trimmed instructions

streamlined things a bit for opus, updated instructions and prose WORKS on claude 3 opus/sonnet, gemini 1.5 pro / 1.0 ultra & gpt-4-32k & gpt-4-1106

includes brand new codeblock panels that are similar in principle to the HTML panels, but smaller in token output. also includes html + text adventure prompts from previous v10

bloat v10 (31/03/24)

updated html instructions, added a vision prompt and a brand new text adventure prompt

(just enable the corresponding prompt + prefill)

(works well with the ST extension)

lite v1.4 (26/04/24)

[experimental update, not really recommended] old link 1 old link 2 v1.4: added suggestions from the thread (clarified user/assistant roles, added perspective toggles)

lite v1.2 (22/04/24)

v1.2: tweaked rp prompt, ujb & prefill, also debloated HTML prompt

added some new "chat toggles"

system toggles (rp prompt, ujb) are totally optional at this point, you can disable them to save ~900 tokens

lite v1.1 (16/04/24)

v1.1: made minor improvements overall. massively improved HTML guidelines to be much more immersive and grounded in the scenario (should stay absolutely true to the context and setting; the model will try and expand with details from lore or it will try to make it up)

HTML toggle prompt size increase from 1200 tokens >> 2400 tokens

opus v1.1a (1/04/24)

v1.1a: bug fixes, making sure it works smoothly with a majority of cards, trimmed examples heavily also removed all mentions of emojis

opus v1.1 (1/04/24)

v1.1: bug fixes for formatting with the extension, trimmed examples

opus v1.0 (31/03/24)

bloat v8 (16/03/24)

rearranged prompts for opus

bloat v7 (07/03/24)

leaked version from sturdy

bloat v1 (19/11/23)

first version of bloatmaxxing

yi-large preset

v1.0, wip (until i get access back)

[experimental] claude rp (31/03/24)

experimental [autistic] prose, heavy usage of alt characters

[experimental] mistral rp (17/03/24)

mistral prompt preset, includes html

alternative, lighter (2.4k tokens) version (16/03/24)

use this if you're a paypig/proxyfag with a quota