лавантиен lavantien

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

PostgreSQL is Enough

Background and Cron Jobs

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:

Conversation Archive: AGI, Ethics & Utopia

A dialogue between lavantien and DeepSeek

Summary

Initial Query: Aspiring for an Anarchist Global Society

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:

Prompting the Reasoning models

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.
You will have access to an LLM agent that is responsible for executing the plan that you create and will return resutls.

Applications Overview

1. Gradient Descent (GD) & Variants (SGD, Adam)

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.

Navigating and Mastering Golang Monorepos: An LLM-Powered Approach

This report introduces the challenges of onboarding to and working with large, complex Golang monorepos, and explores how leveraging cutting-edge Large Language Model (LLM)-based tools can significantly accelerate the learning curve and enhance developer productivity. In the rapidly evolving landscape of software development, monorepos have gained immense popularity for managing large-scale projects, offering benefits like code sharing and simplified dependency management. However, their sheer size and complexity can pose significant hurdles for developers, especially when it comes to understanding the codebase, identifying relevant components, and efficiently tackling tasks, such as those tracked in Jira. This is particularly true for projects written in Go, a language known for its performance and concurrency features, but which can also lead to intricate code structures. As of February 2025, the

	// 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)_/¯

	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

	/.ipynb_checkpoints
	/cheatvenv