Maharshi-Pandya

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

supersational

while true; do
  osascript -e '
tell application "System Events"
    if exists process "Claude" then
        tell process "Claude"
            if exists button "Allow for This Chat" of group 2 of group 1 of group 2 of group 1 of UI element "Claude" of group 1 of group 1 of group 1 of group 1 of window "Claude" then
                click button "Allow for This Chat" of group 2 of group 1 of group 2 of group 1 of UI element "Claude" of group 1 of group 1 of group 1 of group 1 of window "Claude"
                log "clicked allow button"
            end if
        end tell

feveromo

Setting Up MCP Servers on Windows

A step-by-step guide to setting up Model Context Protocol (MCP) servers for Claude Desktop on Windows.

Prerequisites

1. Install Node.js (v18.x or later)
   • Download from: https://nodejs.org/
   • Verify installation by opening Command Prompt (CMD) and running:

     node --version
     npm --version

awni

cmake_minimum_required(VERSION 3.27)

project(example LANGUAGES CXX)

set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)

find_package(
  Python 3.9
  COMPONENTS Interpreter Development.Module

karpathy

# -----------------------------------------------------------------------------
# AI-powered Git Commit Function
# Copy paste this gist into your ~/.bashrc or ~/.zshrc to gain the `gcm` command. It:
# 1) gets the current staged changed diff
# 2) sends them to an LLM to write the git commit message
# 3) allows you to easily accept, edit, regenerate, cancel
# But - just read and edit the code however you like
# the `llm` CLI util is awesome, can get it here: https://llm.datasette.io/en/stable/

gcm() {

awni

# Requires:
# pip install pyobjc-framework-Metal
import numpy as np
import Metal

# Get the default GPU device
device = Metal.MTLCreateSystemDefaultDevice()

# Make a command queue to encode command buffers to
command_queue = device.newCommandQueue()

awni

wilderlopes

List of terminal-based developer tools that deliver value in 30 seconds

• miniogre: from source code to reproducible envionments, in seconds
  • pip install miniogre
  • Go to project folder
  • Run miniogre run
• freeze: generate images of code and terminal output
  • brew install charmbracelet/tap/freeze
  • freeze --execute "ls -ltra"
• uv: An extremely fast Python package installer and resolver, written in Rust

rafaelrc7

######################### Preamble ###########################################
SHELL := bash
.ONESHELL:
.SHELLFLAGS := -eu -o pipefail -c
.DELETE_ON_ERROR:
.SECONDEXPANSION:
MAKEFLAGS += --warn-undefined-variables
MAKEFLAGS += --no-builtin-rules
MAKEFLAGS += -j$(shell nproc)

lewtun

# This is a modified version of TRL's `SFTTrainer` example (https://github.com/huggingface/trl/blob/main/examples/scripts/sft_trainer.py), 
# adapted to run with DeepSpeed ZeRO-3 and Mistral-7B-V1.0. The settings below were run on 1 node of 8 x A100 (80GB) GPUs.
#
# Usage:
#   - Install the latest transformers & accelerate versions: `pip install -U transformers accelerate`
#   - Install deepspeed: `pip install deepspeed==0.9.5`
#   - Install TRL from main: pip install git+https://github.com/huggingface/trl.git
#   - Clone the repo: git clone github.com/huggingface/trl.git
#   - Copy this Gist into trl/examples/scripts
#   - Run from root of trl repo with: accelerate launch --config_file=examples/accelerate_configs/deepspeed_zero3.yaml --gradient_accumulation_steps 8 examples/scripts/sft_trainer.py