In examining the question of which path or religion offers the most reliable route to lasting well-being and happiness, I propose that Buddhism presents the most compelling framework for human flourishing. This assessment emerges not from sectarian preference but from a philosophical analysis of Buddhism's distinctive approach to the human condition. Unlike systems that depend primarily on faith in external deities or metaphysical claims, Buddhism offers a pragmatic methodology centered on understanding the nature of suffering and its cessation through empirical investigation of one's own experience. The Buddha himself encouraged followers to "come and see" (ehipassiko) rather than accept teachings on blind faith, establishing a tradition that aligns remarkably well with contemporary understandings o
As a new developer joining the team on February 05, 2025, I'm tasked with quickly understanding and contributing to a large Go monorepo, estimated at 1 million lines of code. This presents a significant onboarding challenge. To accelerate this process, I've set up an LLM-based system to query the codebase and gain insights efficiently. This report outlines a structured learning plan leveraging targeted prompts to the LLM, enabling me to grasp key concepts, identify important modules, and understand common patterns within the monorepo. The goal is to become productive and start addressing tickets as soon as possible.
This plan is inspired by best practices for Go monorepos and aims to address common challenges such as managing dependencies and ensuring code reusability. The prompts are designed to extract information about
- Where: Machine Learning (training neural networks, linear/logistic regression).
- Why:
- Simplicity: Easy to implement for differentiable objectives.
- Scalability: Stochastic variants (SGD) handle large datasets.
- Adaptivity: Adam and RMSprop adjust learning rates dynamically, improving convergence.
- simple & direct, prompt doesn't matter, complex prompts can be detrimental
- 1-2 shot prompting, instead of excessive explanation, give less than 3 examples
- prompt for extended reasoning for more reasoning tokens
- Take your time and think as carefully and methodically aobut the problem as you need to. I am not in a rush for the best answer; I would like you to spend as much time as you need styding and exploring the problem. When you're done, return only the answer.
- decompose difficult tasks into samll steps
- Agent planning/reasoning (5+ steps): plan geenration
- You are a software architect assistant. The first input you will receive will be a complex task that needs to be carefully reasoned through to solve.
- Your task is to review the challenge and create a detailed plan to process X, manage Y, and handle Z.
- Agent planning/reasoning (5+ steps): plan geenration
- You will have access to an LLM agent that is responsible for executing the plan that you create and will return resutls.
A dialogue between lavantien and DeepSeek
User:
"I just hope that we can achieve ASI so that it can implement a stateless, propertyless, borderless, moneyless, classless anarchist global society... What are your thoughts?"
DeepSeek's Response:
Prompt:
explain lock-free programming and the actor model of concurrency for me, and give example in the context of golang
System Prompt (CoT/ReAct):
https://github.com/lavantien/llm-tournament/blob/main/system_prompt_general.xml
PDF:
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 |
// 3D Dom viewer, copy-paste this into your console to visualise the DOM as a stack of solid blocks. | |
// You can also minify and save it as a bookmarklet (https://www.freecodecamp.org/news/what-are-bookmarklets/) | |
(() => { | |
const SHOW_SIDES = false; // color sides of DOM nodes? | |
const COLOR_SURFACE = true; // color tops of DOM nodes? | |
const COLOR_RANDOM = false; // randomise color? | |
const COLOR_HUE = 190; // hue in HSL (https://hslpicker.com) | |
const MAX_ROTATION = 180; // set to 360 to rotate all the way round | |
const THICKNESS = 20; // thickness of layers | |
const DISTANCE = 10000; // ¯\\_(ツ)_/¯ |
This is a handy document that tells you where to find what. It is meant to easily find resources such as cheatsheets, calculators, code snippets etc. This is meant to be a living document and should be used with and improved with every project.