'Rote Adaptiveness', the capability of automatically being adaptive seems like an oxymoron and is also not as well investigated. But this capability is critical to General Intelligence.
How can a skill that is performed without comprehension be one that is also adaptive? This sounds counterintuitive, yet we see this all the time in the field of software development.
Decades ago, it was well understood that software development should not be executed not like a factory floor. Instead, software development is more like a discovery process. Furthermore, we can invent processes to accelerate this discovery process.
In other words, good software development involves the automation of discovery. So rote adaptiveness is not a vague idea but there are plenty of examples of processes that improve the navigability of the unknown.
In fact, navigation is an apt metaphor for rote adaptiveness. Effective navigation demands good tactics so as to avoid walking in circles.
The motivation why I find rote adaptiveness interesting is the realization that any collective intelligent whole must have adaptive parts to operate robustly and effectively. But the parts themselves cannot be intelligent otherwise we have an infinite regress.
So we must build a library of tactics that lead towards greater adaptiveness. Tactics that can be performed without the need of comprehension. Tactics that can be performed by non-intelligent parts.
How does one build a system that is competent in addressing uncertainty? At a minimum, you need something that can learn (without comprehension). This learning system must then train in contexts of complex adversaries. Does this not remind one of a GAN?
What I want to curate however is a library of adaptive tactics. I hope to discover a meta-framework that can serve as guidelines for developing more intelligent machines.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Carlos E. Perez

Carlos E. Perez Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @IntuitMachine

Feb 17
It is a common belief that human civilization evolution is predominantly influenced by the religious and philosophical ideas of the past. I don't think this is true, civilization is influenced by technology. Let me explain.
Technology influences the direction of civilization because we are 'forced' to adopt it. We adopt technology because it is useful. We adopt it regardless of our religious or philosophical biases.
The Amish, as part of their religion. deliberately avoid modern technologies. With the exception, however, if it is used for work. So it is not uncommon to see them with smartphones and credit card readers to facilitate their commerce.
Read 18 tweets
Feb 17
It's already been two years since John Vervaeke completed his 50 episodes 'Awakening from the Meaning Crisis'. I revisited one lecture and realized that it's much better than when I originally watched it!
My original motivation for watching his lectures was to see if I can gain more insight on human cognition in the hopes of understanding general intelligence. So I skipped most of his lectures until episode 26.
The previous episodes are a historical account of how humans evolved their thinking of how they would navigate this world. I tend to not care for historical accounts because they spend time on dead ends.
Read 10 tweets
Feb 16
Surprise! Deep Learning may be the technology that saves us from extinction due to climate change! So for all those detractors, I would like to see your public apologies. wired.co.uk/article/deepmi…
Perhaps it took so long to create a sustainable fusion reactor because humanity did not have the automated cognitive technology to adjust the magnetic field on the fly. What if nuclear fusion was a similar problem to balancing a ball on a pole?
Researchers have thought the problem could be solved by bigger and more powerful reactors. But with this new approach, there's a possibility for smaller fusion reactors. Reactors that are enough to fit in mobile vehicles!
Read 9 tweets
Feb 16
A horrible thing happened right after the printing press was invented. 4.5 to 8 million people died in Europe due to 30 years of warfare. en.wikipedia.org/wiki/Thirty_Ye…
A war spawned by the conflict between truth originating from traditional authority and truth originating from literal text. A new war is brewing between the theists and the atheists. Subjective truth versus objective truth.
To avoid this war, Science must recognize the subjective.
Read 5 tweets
Feb 16
Why is it so common that bigoted people all too often expose their cognitive flaws?
I'm also Asian, but I confess that the lack of exposure to faces of different races does affect your recognition abilities. One would think that it's only Asian faces, but it's any face of an unfamiliar kind. Recognizing faces is an intuition that requires practice.
Yesterday, my wife was spotted by a co-worker in a crowded shopping area. This was despite wearing a facemask and a heavy jacket. People can recognize other people with the smallest of cues.
Read 8 tweets
Feb 15
Surprisingly, the unorthodox approach of the USA to release immediately on the ground assessments of Russian military movements seems to be working! Does anyone have a good handle on this game theory?
Conventionally, one does not reveal what one knows to the adversary. Doing so reveals your information collection capabilities and gives your adversary more information that can be used to your disadvantage.
Revealing information ahead of time is an unexpected tactic that puts Russian forces off balance. The Russian strategy is to use temporary gaps of information to their advantage. They leveraged this in their invasion of Crimea by not making it clear who the 'green men' were.
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

:(