Mostly Harmless AI - the book that explains you the AI without the bullshit

12 hrs ago • Alejandro Piad Morffis

4

The 80% AI Reliability Horizon

The real number every AI engineer should be tracking

May 21 • Alejandro Piad Morffis

11

3

1

It's Tokens all the Way Down

How language models understand image, audio, and video.

May 19 • Alejandro Piad Morffis

23

7

8

70 Years of AI History in 10 Minutes

A summary to the updated zero-th chapter of Mostly Harmless AI v2.

May 18 • Alejandro Piad Morffis

14

3

How Large Languages Models Are Really Made

The full road from text data to reasoning models, explained visually with zero math or code.

May 11 • Alejandro Piad Morffis

37

6

7

How to write a CLI an agent will actually use

Making tools that are safe by design, not convention.

May 7 • Alejandro Piad Morffis

12

1

1

The Anatomy of a Linguistic AI Agent

From single-turn LLM to long-horizon autonomous AI.

May 4 • Alejandro Piad Morffis

16

1

4

April 2026

Realtime 3D in Pure Python + Numpy

Just a fun side-project that went way too far-as it happens.

Apr 7 • Alejandro Piad Morffis

20

4

2

AI Coding Agents, Deconstructed

The four hidden layers that separate tools that help form tools that hinder

Apr 2 • Alejandro Piad Morffis

29

4

1

March 2026

How I'm Using AI Today

Yes, another take on this. I promise you this one is a bit different.

Mar 2 • Alejandro Piad Morffis

16

11

February 2026

Drawing (not so) Beautiful Diagrams with Pure Python

Ups, I did it again :)

Feb 13 • Alejandro Piad Morffis

15

5

January 2026

Introducing Tesserax

A pure Python, developer-friendly library for academic drawing.

Jan 31 • Alejandro Piad Morffis

24

31

3