# How to Reason Bayesian Style

## An introduction to and derivation of Bayes’ Theorem

Let’s say we know that 1 in 200 women have breast cancer. We don’t know which women actually have it, so we develop a test that screens for breast cancer. Our test has the following relevant statistics:

Now, a woman walks in our test room and tests positive. What is the probability that she actually has breast cancer? I encourage the reader to actually try and come up with an answer.

We want…

# How to do Propositional Logic

## An intuitive introduction

If we are to learn how to build an ASI, it’s important to know how to think. Not only to think logically and rationally about building an ASI — which is very important — but also because we need to know how an ASI should think. Propositional logic deals with very fundamental ideas of “truth”, and I think it’s important to start here. Later we will discuss more advanced ideas and see how they follow from Propositional logic.

Propositional logic deals with

# Introduction: How to Build an ASI

## What to expect in this highly ambitious publication

First things first: what is an ASI? ASI is short for Artificial Superintelligence, which informally means any non-biological thing (in practice, a computer, embodied or not) that’s more intelligent than even Albert Einstein, John von Neumann and your personal favorite genius. Intelligent here refers to one’s ability to reach one’s goals in a wide variety of environments; we will go deeper into this definition in a later post, but this will do for now. Given our brain’s small size and low signaling speed, it seems unlikely that peak human intelligence is the maximum level physically possible. …

# The Size of Quetzalcoatlus

## The biggest flying animal ever to have lived

The Cessna 172R “Skyhawk” is an airplane. Weighing about a ton, it has a wingspan of exactly 11 meters. Although the Skyhawk is of course a small airplane, you’d expect no animal to be able to match such a wingspan.

Well, you’d be wrong. Meet Quetzalcoatlus — in a manner of speaking, because this reptile went extinct around 66 million years ago, when a giant asteroid hit our planet. This caused the extinction of all pterosaurs (of which Quetzalcoatlus was a member). …

# The Speed of the Cheetah

## The fastest land animal alive

At the 2009 IAAF World Championships, Usain Bolt showed the world his amazing ability to run 100 meters in 9.58 seconds. While his average running speed in this event was 37.58 km/h, his top speed was an astonishing 44.72 km/h.

While Usain Bolt is in all probability the fastest human ever to have lived, his speed record is dwarfed by that of the fastest land animal alive: the cheetah. In 2012, 11-year-old cheetah Sarah set the cheetah 100 meter record at 5.95 seconds, with a top speed of 98 km/h. …

# How to Implement the Hill Climbing Algorithm in Python

## A step-by-step tutorial on how to make Hill Climbing solve the Travelling salesman problem

Hill climbing is a mathematical optimization algorithm, which means its purpose is to find the best solution to a problem which has a (large) number of possible solutions. Explaining the algorithm (and optimization in general) is best done using an example. In the Travelling salesman problem, we have a salesman who needs to visit a number of cities exactly once, after which he returns to the first city. The distances between each pair of cities are known, and we need to find the shortest route. As you can imagine, there is (often) a large number of possible solutions (routes) to…

# Andrew Ng Is Wrong About Artificial Superintelligence

## The right time to think about AI Alignment is right now

“Worrying about AI evil superintelligence today is like worrying about overpopulation on the planet Mars. We haven’t even landed on the planet yet!” — Andrew Ng

Elon Musk has warned us. Stephen Hawking has warned us. Many others are worried about it. Artificial Superintelligence may sound like the stuff for science fiction movies, but it could very well be a reality this century. And according to the aforementioned thinkers and myself, it could mean the end of humanity. However, many people think we shouldn’t be worried! One of them is, you guessed it, Andrew Ng.

For those of you who…

# The AI Box Experiment

What happens when we create an Artificial Superintelligence (ASI)? Many great thinkers have warned us of the danger of human extinction, but we could just turn the ASI off if we wanted to, right? Well…

# The AI Box Experiment

## Why a Superintelligence can’t be contained

It’s 2040. After a decade of research and dedicated programming, you believe your team has created the World’s first Artificial General Intelligence (AGI): an Artificial Intelligence (AI) that’s roughly as intelligent as humans are among all their intellectual domains. Since one of these intellectual domains is obviously programming AIs, and since your AGI has access to its own source code, it soon starts to make improvements on itself. After multiple cycles of self-improvement, this leads to it becoming an ASI: Artificial Superintelligence, an intelligence much greater than any we know.

You have heard of the dangers posed by ASI: thinkers…

# The Unfortunate Power of Deep Learning

## As our systems become more and more capable, we need to be able to know they will make the right decisions

In May 1997, Deep Blue, a Chess computer developed by IBM as the next stage of Carnegie Mellon University’s Deep Thought project, defeated then reigning World Chess champion Garry Kasparov with a score of 3.5–2.5. Deep Blue used a classic, explicitly programmed search procedure (minimax) to play Chess: it based the strength of each move on the best possible counter-move.

Twenty years later, Google Deepmind’s AlphaGo Master, a Deep Learning system, beat Ke Jie, the then number 1 Go player in the World, in a three-game Go match. Even though the World was shocked, AlphaGo Master would get successors which…

## Hein de Haan

AI expert, Futurist and Space Enthusiast

Get the Medium app