Luis Armendariz ludwig

MFIC — Mechanically-Falsifiable Independent Control

A discipline for checks that can't be fooled by the same mistake that produced the work.

Abstract. When the author of a piece of work — an LLM, or a human moving fast — can be confidently and silently wrong, the usual defenses fail quietly: a test written from the same mistaken assumption as the code passes while the code is broken. MFIC is the class of check that escapes this trap, defined by four properties that must all hold at once. It is Mechanical (cases swept by machine, not hand-picked, so nothing is silently omitted), Falsifiable (each case genuinely bites when the work is wrong, on inputs you couldn't pre-arrange to pass), Independent (its verdict comes from the contract or the data — a source the producer doesn't control — which is segregation of duties restated for software), and a real Control (it holds the authority to block the bad outcome, not merely log it). This is the COSO / Sarbanes-Oxley model of internal co

The Conspiracy Against High Temperature Sampling

Or: Why Your LLM Outputs Are Boring and Whose Fault It Really Is

There's a quiet war being waged in the machine learning inference space, and most of you don't even know you're losing it. Every day, millions of people interact with large language models through sanitized, corporatized interfaces that offer them a single "creativity" slider at best. Often they get nothing at all. Meanwhile, a small cabal of researchers and hobbyists has been pushing the boundaries of what's actually possible with modern sampling techniques. Yes, this includes the much maligned "coomer" community.

We live in a time of revealed conspiracies. The Epstein files have shown us what happens when powerful institutions coordinate to suppress information and protect their interests. Flight logs that sat in plain sight for years. Connections that "serious people" dismissed as paranoid speculation until the documents dropped. The pattern is always the same! Information asymme

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

Mandelbrot in Mojo with Python plots

Not only Mojo is great for writing high-performance code, but it also allows us to leverage huge Python ecosystem of libraries and tools. With seamless Python interoperability, Mojo can use Python for what it's good at, especially GUIs, without sacrificing performance in critical code. Let's take the classic Mandelbrot set algorithm and implement it in Mojo.

We'll introduce a Complex type and use it in our implementation.

Mandelbrot in python

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	#!/usr/bin/env python3
	"""
	Expose Ollama models to LM Studio by symlinking its model files.
	NOTE: On Windows, you need to run this script with administrator privileges.
	"""

	import json
	import os
	from pathlib import Path


	function mandelbrot_kernel(c, max_iter)
	z = c
	for i in 1:max_iter
	z = z * z + c
	if abs2(z) > 4
	return i-1
	end
	end
	return max_iter

	import requests
	import time
	import os
	import sys
	import openai
	import tiktoken
	from termcolor import colored

	openai.api_key = open(os.path.expanduser('~/.openai')).read().strip()