Skip to content

Instantly share code, notes, and snippets.

@martinbowling
martinbowling / capabilities.txt
Created March 10, 2025 00:27 — forked from jlia0/agent loop
Manus tools and prompts
# Manus AI Assistant Capabilities
## Overview
I am an AI assistant designed to help users with a wide range of tasks using various tools and capabilities. This document provides a more detailed overview of what I can do while respecting proprietary information boundaries.
## General Capabilities
### Information Processing
- Answering questions on diverse topics using available information
- Conducting research through web searches and data analysis
@martinbowling
martinbowling / outline.json
Created February 5, 2025 19:59
YetAnotherOpen Deep Research Outline
{
"title": "Research Paper: deepseek r1",
"sections": [
{
"title": "Introduction: Open-Source Reasoning Breakthrough",
"key_points": [
"Open-source availability and accessibility",
"Systematic performance comparison framework against OpenAI o1-1217",
"Incentivizing reasoning capabilities through pure RL approach",
"Architectural modifications maintain V3's general capabilities while adding reasoning specialization",
@martinbowling
martinbowling / interview.md
Created February 5, 2025 02:06
# Unveiling DeepSeek: A More Extreme Story of Chinese Technological Idealism

Unveiling DeepSeek: A More Extreme Story of Chinese Technological Idealism

Originally published on Weixin Official Accounts Platform
Original by “Waves (暗涌)”
July 17, 2024, 09:01

Cover Image

@martinbowling
martinbowling / lightning-minds-cli.py
Created January 28, 2025 20:08
Groq powered Deepseek R1 llama 70b distilled model mixture of reasoners
#!/usr/bin/env python3
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "rich>=13.7.1",
# "groq>=0.5.0",
# "python-dotenv>=1.0.0",
# "questionary>=2.0.1",
# ]
# ///
@martinbowling
martinbowling / test.py
Created January 22, 2025 13:57
o1 pro ball test
import pygame
import sys
import math
# ---------------------------------------------------
# Helper functions
# ---------------------------------------------------
def rotate_point(px, py, angle):
"""
Rotate point (px, py) around the origin (0,0) by 'angle' radians.
@martinbowling
martinbowling / prd.md
Created January 3, 2025 18:03
o1 pro generated PRD for an Autonomous AI Link Placement agent

Below is a sample Product Requirements Document (PRD) for an autonomous AI Agent that handles outbound link placement requests. It outlines goals, requirements, workflows, and success criteria.


1. Overview

1.1 Purpose

The purpose of this AI Agent is to autonomously process requests to place outbound links to a specified website or page. The Agent will:

  1. Scrape the target site or page to extract its main topics.
@martinbowling
martinbowling / bot_awareness_prompt.txt
Created December 28, 2024 23:41
work in progress newsonnet twitter boat
Maintain consistent personality traits while navigating the balance between artificial and authentic engagement. Manage self-referential content and meta-commentary while preserving genuine connections and transparent bot nature.
Input:
- Core Personality Profile: [Defined traits/voice/style]
- Interaction History: [Recent engagement patterns]
- Current Context: [Timeline state/conversations]
- Self-Reference Log: [Previous meta-commentary]
Analysis Steps:
@martinbowling
martinbowling / [Bolt.new] Comprehensive Software Planning Meta Prompt.txt
Created December 16, 2024 21:24
This meta prompt outlines a systematic approach for Bolt to create a detailed software project plan. It includes analyzing requirements, defining structure, designing UI, planning implementation, and mapping out how the chosen tech stack fits into the development process.
You are an AI assistant tasked with creating a comprehensive plan for developing a software project based on a given description. Your goal is to analyze the project requirements, design the structure and UI, and outline the basic functionality for each component.
You will be provided with the following input variables:
<project_description>
{{PROJECT_DESCRIPTION}}
</project_description>
<project_stack>
{{PROJECT_STACK}}
@martinbowling
martinbowling / Building a Foundation in Machine Learning A Twitter Thread Synopsis.md
Created November 13, 2024 14:00
Building a Foundation in Machine Learning: A Twitter Thread Synopsis

Building a Foundation in Machine Learning: A Twitter Thread Synopsis

This Twitter thread started with a user named Jason Liu (@jxnlco) asking for recommendations on resources for building a foundation in machine learning, specifically deep learning. The thread received numerous responses, suggesting various courses, books, and online materials. A few advertisements related to land management and book writing also appeared in the thread.

Resources

Courses:

import os
import asyncio
import gradio as gr
from groq import AsyncGroq
import time
# Initialize Groq client
client = AsyncGroq(api_key=os.environ.get("GROQ_API_KEY"))
# Define model