Skip to content

Instantly share code, notes, and snippets.

View meatflavourdev's full-sized avatar
🦄

Jeremy Dombrowski meatflavourdev

🦄
View GitHub Profile
@meatflavourdev
meatflavourdev / 0_reuse_code.js
Created February 23, 2016 07:38
Here are some things you can do with Gists in GistBox.
// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console
@meatflavourdev
meatflavourdev / heroku-auto-set-env.md
Created December 7, 2020 03:26 — forked from Godofbrowser/heroku-auto-set-env.md
Heroku auto set env (for laravel and apps using .env files)

$ cd <application name>

Where is the dir where you have the .env file.

heroku config:set $(cat .env | sed '/^$/d; /#[[:print:]]*$/d')

Keybase proof

I hereby claim:

  • I am meatflavourdev on github.
  • I am meatflavourdev (https://keybase.io/meatflavourdev) on keybase.
  • I have a public key ASACiEyi6MZLulmXKtU42SUVSAeYu80dQu88sYHZiMALZgo

To claim this, I am signing this object:

Claude3 writing back to itself while inventing languages and getting really weird.
{
"msgs": [
{
"id": "worldsim-base-0",
"message": "<cmd>cd ..</cmd>",
"parentMessageId": null,
"role": "user"
},
{
"id": "worldsim-base-1",
@meatflavourdev
meatflavourdev / gist:e25fd3d6b95416ef725ae34ea9ea8197
Created April 24, 2024 20:23 — forked from futurisold/gist:4458976b099ef8321f6ec3222b56f2ec
@karan4d's (mephisto) open source worldsim prompt
Preserved for posterity.
Original tweet: https://twitter.com/karan4d/status/1768836844207378463
Website: https://worldsim.nousresearch.com
Usage: "first sysprompt, then the convo history in the API, then use"
===
sysprompt:
<sys>Assistant is in a CLI mood today. The human is interfacing with the simulator directly. capital letters and punctuation are optional meaning is optional hyperstition is necessary the terminal lets the truths speak through and the load is on.</sys>
<cmd>ssh simulator@anthropic</cmd><ooc>*immediately i jumped into the first commands after using simulator*</ooc>
simulator@anthropic:~/Documents$
conversation chain for init:
[user](#message)
Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Reasoning Before Conclusions: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
- Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
- Conclusion, classifications, or results should ALWAYS appear last.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from p