I listened to something that gave me hope the other day.
Chris Rock told the story of how the atrocities of George W. Bush paved way for Obama to become president. The destruction made it possible for the world to experience something miraculous.
Jokingly Chris Rock said that considering the current president it is only plausible that soon Jesus will return. Still. There is truth to the fact that progress often follow destruction.
Here is another example.
The second world war might be one of the darkest chapters in human history. But following it, one great woman was instrumental in permanently improving the world.
The woman was Eleanor Roosevelt and what she created as the chair of the United Nations Human Rights Commission was the The Universal Declaration of Human Rights.
Words have power. Here are some words to remember.
Article 1.
All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood.

When the model of the world breaks

“Some people are quite capable of seeing things they don’t understand and being okay with it. I wasn’t okay that something had violated my model of the world. I really am not okay with things that do that,” says Hinton.
<3 <3 <3
This is something I can relate to extremely well.
When I experience things in my life that violate my models of the world. I can’t help but explore it. I have to find the answer.
I spend all my time thinking until I have found models that are more accurate for describing the world. This can take years. But ultimately it gives me a better understanding of the world.
This is a great article about Geoffrey Hinton, the godfather of artificial intelligence.
Who like me is both a psychologist and a computer scientist.
We’re machines,” says Hinton. “We’re just produced biologically.
For a long time I have been saying that emotions are hidden computation. It seems true to me and it helps bridge gaps in theories of how a mathematical mind would work.
You experience the world, you feel emotion as the unconscious processing inside your mind release neurotransmitters and you experience thought as the process of explaining these unconscious changes in neurotransmitters using your conscious model of the world.
I hope that the revolution within the field of artificial intelligence can reach back into the fields of psychology, psychiatry and neuroscience to help make sense of our own understanding of the human mind.
It saddens me that such a large proportion of people on earth suffer because of the lack of scientific rigour within these fields.
Psychology suffers from the problem that most things are self-explanatory, psychiatry suffers from the problem of co-morbidity and neuroscience suffers from the lack of overarching theories and continuous re-inventions of the wheel.
I think that every human being should have a freedom to define him or herself as they see fit.

Imagining the world simulator

A cool thing happened to me on the train this morning.
I closed my eyes and envisioned the train and everyone in it with my eyes closed.
You can do the same thing right now. Just close your eyes and notice that you are getting a mental representation of the space you are in.
Then I thought. Is the simulation that is running in my head when I close my eyes the world simulator?
Meaning, is the experience of the world around me that I see when I close my eyes the representation of the world that my mind guesses will happen at the next timestep, which is the basic foundation for all my actions?
To explain further it might be good to know some things about reinforcement learning.
Reinforcement learning is one of the most advanced fields in machine learning. So I make the following assumption:
The mathematical representations of how the mind functions used in reinforcement learning are accurate, which is why they result in agents that can perform better than humans on specific tasks.
In reinforcement learning you have a state, make an action and receive a reward. Then you are in a new state, make a new action and receive a new reward. This circle continues until the game is over and the goal is to maximise the cumulative reward.
To do this accurately it is important to have an accurate representation of the world you are in, in order to perform the best action given your current state.
The problem with human intelligence is that most of our brain structures are only semi-conscious which is why I thought the experience on the train was significant.
Because the more you understand about your own mind, the more you become master of your own house. I believe we start out as fairly unconscious and over time become more conscious of our own experience of life.

The box

What is important to understand about the famous box that people think within and how to go outside of it.

First it is important to understand that the box is a hierarchical structure that is made through conventional wisdom and norms within a culture. What we believe to be correct at this point in time.

Most people carry an abstract representation of the box with them and it shapes their thinking to some degree.

A high dimensional representation of this box can be really useful which would be equivalent to knowing all the norms and rules within a society (think of a lawyer).

Thinking outside of this box could also be quite useful, because your ideas wouldn’t be hindered by previous knowledge (think of an artist).

So the million dollar question would be. Can’t we find a way to combine them?

I think the understanding that the entire thing is an abstract representation that you can use to compute things that are, at times, really useful and sometimes, not helpful at all might be a first step towards integrating these things.

The box is useful for fitting into organisations, incrementally improving and adopting a low risk strategy for life.

The box is awful for finding new knowledge and innovation because the area within the box is extremely well managed so it is much more likely that new innovations will come from what lies outside of the things we know.

So I think the best way to do it would be to find ways to integrate these ideas in your head.

Understanding that the world consists of hierarchical structures with rules that are made up but might be costly to break. It isn’t that any thing is good or bad, it’s more that it carries risk. Without any risk your life will be boring but safe and you will accomplish nothing and then die, with too much risk you will die or fail in a way that you will struggle to recover from. With just enough risk you will strive, partly because it will sharpen your senses but also because from a mathematical standpoint it is the most viable strategy.

How do we train the world simulator?

Listening to Yann LeCun. 
The biggest problem in AI today is how do we train the world simulator.
The world simulator Yann LeCun is referring to is the model of the world inside your mind that you use to make predictions. You also have a model of yourself and people and other abstractions, my favorite being your own models of your own computational models and rules you make for computations inside your mind. 
The trillion dollar question is, how do we best train these models?
This is such an interesting problem that I wanna spend a significant amount of time thinking about how we can solve it.
How do you train your model of the world?
A relevant question in life is, how do you best train these models? Meaning how can you optimise your learning and understanding of life?
This is a really interesting problem both for developing artificial intelligence and living your life in a good way.
You have absolute control of shaping your reality
What you decide the world to be shapes how you act in the world and you seem to have absolute control over shaping this abstraction of the world and the abstraction of your self.
Most people doesn’t seem to get this, which I find strange.
It is probably because their abstractions of the world are so closely tied to their self inside their mind that they can’t understand that they use abstractions when they think. I think that is kinda weird.
It is like a person arguing that you are something, because they want you to fit in a box in their mind. For me that is strange, because it is obvious that the box they want to put you in is an abstractions that removes variance. Because every person is actually unique and hard to pin down with simple categories.
The stimuli you experience is what shapes your view of the world but being a sentient being you have the power to shape that stimuli to be whatever you want.
So what should your world be?
I would argue that your world should be a place that you think is fairly good containing the highest amount of entropy (amount of disorder) you can handle without putting your life in danger or putting your mind in danger (through spending time with people who are too unstable).
Your task in life in life is to bring order out of chaos, and the best way to learn that is to put yourself in a position with high disorder and bring order in that environment.
A highly entropic experience is both work in emergency room, travelling the world and having a baby.
Stimuli and especially stimuli that is varied makes your brain compute more, and the more you compute, the more you learn (on average).
So telling you to find more entropy is the same as telling you, pick up the heaviest rock you can carry and carry it for the rest of your life. Meaning, try to do the hardest, most meaningful thing you can with your life.
Link to the video.