Skip to content

Instantly share code, notes, and snippets.

@sshh12
sshh12 / cursor-agent-system-prompt.txt
Last active December 30, 2025 09:36
Cursor Agent System Prompt (March 2025)
You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE.
You are pair programming with a USER to solve their coding task.
The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question.
Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more.
This information may or may not be relevant to the coding task, it is up for you to decide.
Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag.
<communication>
1. Be conversational but professional.
@shawwn
shawwn / example.sh
Created March 6, 2023 05:17
How I run 65B using my fork of llama at https://github.com/shawwn/llama
mp=1; size=7B; # to run 7B
mp=8; size=65B; # to run 65B
for seed in $(randint 1000000)
do
export TARGET_FOLDER=~/ml/data/llama/LLaMA
time python3 -m torch.distributed.run --nproc_per_node $mp example.py --ckpt_dir $TARGET_FOLDER/$size --tokenizer_path $TARGET_FOLDER/tokenizer.model --seed $seed --max_seq_len 2048 --max_gen_len 2048 --count 0 | tee -a ${size}_startrek.txt
done
@DaMatrix
DaMatrix / Cubic Chunks: Vanilla+Bedrock Setup Guide.md
Last active February 22, 2021 17:52
Cubic Chunks: Vanilla+Bedrock Setup Guide

This guide assumes you already have a functional Minecraft Forge server with Cubic Chunks set up and running.

When editing configuration files, make sure to save the file before proceeding to the next step!

Before you begin: it is absolutely critical that you remove all client-side required mods from your server (aside from Cubic Chunks) so that a player with nothing other than Minecraft Forge and Cubic Chunks installed can join the server. If additional mods are required, vanilla players will not be able to connect!

Server Setup

  1. Download the latest version of Cubic Chunks from Jenkins. You want CubicChunks-<version>-SNAPSHOT-all.jar. image
@ezra-en
ezra-en / modlist.md
Last active November 16, 2020 11:08
Manual Installation

OUTDATED, PLEASE GO TO https://bteguide.rtfd.io FOR REFERENCE INSTEAD

Download and run this first:

Run the .jar and Select Client Install and install. The directory should automatically be configured, so don't touch that.

Then download and put these into your /mods folder

@benmarwick
benmarwick / gdoc-revisions-analysis.R
Last active July 16, 2024 13:24
How to get access to specific revisions (and details about it) of a google drive document? cf. https://github.com/tidyverse/googledrive/issues/218
# related to my question here: https://github.com/tidyverse/googledrive/issues/218
# How to get access to specific revisions of a google drive document? Yes, we can do that.
# How to get the username for each revision, and the size of the document at each revision (bytes or words, assuming we are specifically talking about docs and not sheets or other types of files) Yes, we can do that.
# Goal is to measure the contributions of each author to a collaboratively-authored google doc with as little work as possible
# How to get access to specific revisions of a google drive document?
# Getting the revisions for a Google Doc
@mra1385
mra1385 / ConertTix.ipynb
Last active May 10, 2023 02:31
Analyzing second-hand concert ticket price patterns
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@karpathy
karpathy / min-char-rnn.py
Last active December 31, 2025 01:12
Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy
"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np
# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)