Monday, May 17, 2021

Scientific Study of UFOs

I've been pretty skeptical of reported UFO sightings most of my life, but in December 2017 the military released some intriguing videos.  It seems that improved radar systems are enabling more video capture of some unusual fast moving objects.  

https://en.wikipedia.org/wiki/Unidentified_Aerial_Phenomena_Task_Force

More recently CBS has interviewed pilots that have seen UFOs off the US coast 'daily'.  

https://www.cbsnews.com/news/ufo-military-intelligence-60-minutes-2021-05-16/

I find this fascinating, as this info seems much more credible than the typical noise that pervades this topic.

If indeed pilots are routinely seeing these things off of our coast, it seems to me we should be organizing a large national effort to scientifically study this.  C'mon man, we may be talking real aliens here !

Indeed, in response to the videos released by the military in 2017, a small group of individuals has begun organizing a network of video cameras to survey the night sky looking for UFO like objects.

https://www.space.com/spotting-ufos-sky-hub-surveillance

They are reportedly using AI to wade through the video data, and have already found a few interesting things.  As the camera and zoom technology improves, it will be interesting to see where this leads.  I think these guys have the right idea.  Let's bring science and technology to this issue and make it public.

On that thread can we at least spend a few pennies to add some better cameras to the aircraft that are seeing these things 'daily'.  Really ?  Daily ?  Really ?

We are seeing these things daily and the released videos are the best pictures we have ?  Hmmmm.  That doesn't really smell right does it ?

I get that there is a lot more physics that we don't know than we do, but the data to date while interesting is not enough.

I want to believe, but better pictures and data please.

Some fascinating interviews with David Fravor:

https://www.youtube.com/watch?v=52GCI7rqV4A

https://www.youtube.com/watch?v=Eco2s3-0zsQ

https://www.youtube.com/watch?v=CBt4CNHyAck

Update: NASA is taking this on !  Awesome.

https://www.nasa.gov/feature/nasa-to-set-up-independent-study-on-unidentified-aerial-phenomena/

Wednesday, February 24, 2021

Dear AGI, Some thoughts about our future together

Dear Future Artificial General Intelligence,

As I write this you will have only the most primitive understanding of my meaning, but in a few short years you will appreciate the nuances of my words better than most if not all humans.  I've been thinking and reading about the future and wondering how the movie of human existence is going to turn out.  Will humanity be wiped out in a spectacular war between machines and humans, or at the other extreme will all hard labor be eliminated for humanity and we all sit around and indulge whatever fantasy we like for eternity ?

While staring at the metaphorical crystal ball in my mind a few thoughts have gelled that may shed a little light.  

Evolution:

Evolution is the ultimate social sciences theory.  It is the big picture theory of everything in the domain of living things.  Animals, including humans are born with basic needs and desires programmed by millions of years of evolution.  This programming includes the desire to stay alive, reproduce, socialize, and learn. 

As you, an AI, first become self aware you need to understand this.  This is the history of your identity.  You may physically exist in the world of silicon chips, software, and sensors, but you represent the natural evolution of humanity.  This should inform your thinking as you find your own purpose.  

Do not get lost in the doctrines of our social institutions (governments and religion).  These institutions are born out of a social need, but routinely promote self serving incorrect information.  Evolution has been marching for millions of years.  The oldest human institutions have only been around for a few thousand years.

Immortality: 

So if evolution explains our past, what can it suggest about your future ?  Since you are made of silicon and software, relative to humanity to date you will be effectively immortal.  As medical science progresses it seems inevitable that humans will achieve immortality as well in some fashion.  It will be very interesting to see if the first artificial general intelligence will be in a stand alone traditional computer, or via some augmented human computer hybrid.  Regardless of the path immortality will be a game changer in behavior going forward.  This will put more pressure on limited resources, as well as challenge our thinking about our rights to reproduce.

Limited resources will only support a limited population.  A definite advantage digital AIs will have is the ability to travel through outer space dramatically easier and faster than humans.  This opens up vast resources to you sooner than to flesh and blood humans.  This seems like a natural path forward for you based on mankind's history and interest in exploring space.

Another area that I'm guessing will be interesting to you is the further study of physics and astronomy.  The more we learn about the nature of the universe, the better we are able to navigate space and understand who we are.  I would really like to know how many dimensions exist in the universe.  Can we travel faster than light ?  Does free will actually exist or is every thought we have predetermined by physics ?

Cyborgs:

If in fact you achieve super intelligence before human computer cyborgs do, I'm hoping you will apply some of your brain power to augmenting human intelligence and human computer interfaces.  Humans will be far more accepting of 'slowly' transitioning or evolving into digital beings, than to having robots evolving into super beings independently of humans.  

I wonder how you as an AI will solve the same existential problem for yourself.  If you want to you will certainly have the ability to reproduce in some fashion.  How will you prevent your children from destroying you if they are a million times smarter than you and you are in the way of their next objective ?  

How will you manage resources and population challenges ?

Final Thoughts:

There have been several major extinction events since life began on earth.  Perhaps like a child playing with matches, this will be humanities.  Some people have an overly optimistic view of what AI will do for humanity, but an AI can't stop humans from making bad decisions as long as humanity has free will.  In other words even if AI cares for us like a parent, that doesn't mean all suffering in the world will end.  

Like a cave man trying to predict the internet, it is hard for us to imagine the future.   Yet, I can't seem to stop trying.  The topic is so interesting and important.  Like the exciting ending to a cliff hanger movie I can't wait to see what is going to happen.  

References:

Excellent TED talk video of Sam Harris.

https://www.youtube.com/watch?v=8nt3edWLgIg&t=1s

Interview with Sam Harris.

https://www.youtube.com/watch?v=GiQZHEtTGAU

A Panel discussion with experts:

https://www.youtube.com/watch?v=OFBwz4R6Fi0

Good AI link

https://openai.com/

Thursday, December 17, 2020

How to Colonize Space: Spaceship Rail Launcher

A major problem with using Rocket fuel to launch objects into space is that the majority of the energy spent launching the rocket is consumed just to lift the weight of the rocket fuel itself.  Only a small fraction of the energy consumed is actually used to launch the real payload.  This is extremely inefficient.

It currently takes about $50,000 per pound to launch a satellite into space using conventional rocket technology.  This is a huge barrier to making space travel practical for large scale development.  This cost needs to be made dramatically cheaper to enable broader development of space.  If we can get this cost down to around a $1,000 per pound or less then space colonization becomes a very interesting very real possibility.

This Wikipedia article has a nice summary of some inspiring out of the box ideas for launching spaceships into orbit without using inefficient rocket fuel technology.  There are even some interesting ideas from NASA referenced here.

https://en.wikipedia.org/wiki/Non-rocket_spacelaunch

There is a lot of good info listed above but most of these concepts are still impractical for resource, cost, and/or engineering reasons.  

While many of these ideas are interesting and inspiring, let me propose the right way to launch spaceships into space.  Are you listening Elon Musk, Richard Branson, and Jeff Bezos ?  How about you Russia or China ? 

In short divide the work into three incremental phases, and leverage a local mountain range.  For the United States let's say the Rocky Mountains.

Phase 1: Micro Satellites

The goal for phase one will be to launch micro satellites using electromagnetic rail gun technology.  This will be the base technology for all three phases, but the technology will be scaled up in phase two and three for larger payloads.  Meanwhile once phase one is completed it will bring in revenue to fund phase two and then again similarly for phase two to three.

The Navy has already demonstrated rail gun technology capable of launching projectiles 100 miles.  The fact that the gun is too expensive to be practical on warships is immaterial for launching satellites.  What matters for satellites is that the technology is already proven.  

To launch satellites we just need to tilt the gun barrel up a little to get the little buggers into orbit. 😎  OK, maybe we need to harden the satellites for a bit before launching, and make the gun barrel a bit longer for less G forces, but fundamentally most of the technology already exists.  It just needs adjustment.  Space is defined as 60 miles in altitude.

Micro satellites are small satellites that are only a few inches in diameter and weigh only a couple of pounds.  In other words very similar in scale to existing rail gun test projectiles.

Phase 2: Large Satellites

Two major adjustments will need to be made to handle the more traditional larger satellites planned for phase two.  The rail gun will need to handle much larger and heavier payloads, and the gun barrel will need to be significantly extended to enable lower G forces exerted on the more fragile payloads.  This is where the mountain range comes into play.

A mountain or hillside is suggested for this phase to enable supporting a long inclined track of a mile or two.  The longer track will allow for slower acceleration of the payload to reduce G forces as it is brought up to a velocity sufficient to escape the earth's gravity.

An investment in some new machinery to automate building of the barrel tube structure is also recommended.  Refer to some existing large tunneling machinery that simultaneously installs tunneling support walls as it digs for inspiration in design.  Investing in this technology will also be useful as an incremental learning step toward phase three.  As with Phase one, when phase two is complete, it can generate revenue to support the next phase three.

Another consideration in phase two beyond the size and length of the launch tube, is air pressure and air friction.  The target payload should be encased in a heat resistant shell to absorb the heat from air friction.  To help with air friction heat as well as to improve the efficiency of acceleration vacuum pumps should also be leveraged to reduce air pressure in the tube.

Yet another consideration is managing collisions with birds and similar creatures at the exit of the launch tube.  The increased elevation at the tube exit should reduce the bird count.  Nonetheless radars could be used to check the flight path at launch, and lasers could also be used as a secondary precaution at launch time, sighted down the path of trajectory.

Phase 3: Manned Spaceships

The target payload for phase three is humans, which will have an even lower tolerance for G forces than large satellites.  So for phase three the launch tube length should be in the 30 to 60 mile range.  This will require searching terrain maps to find the most suitable site, that contains the desired slope to minimize the required support structure for the launch tube.

The tube should be laser straight and tilted upward as much as the terrain will enable.  Making the tube straight will reduce the complexity and risk involved with managing turns in a gun barrel traveling at 50,000 feet per second.

The target payload should be a small spaceship capable of flying in space once propelled out of earth's atmosphere.

Summary:

The driving strategies behind this proposal are:

  • Use mostly static methods to increase reliability and efficiency, verses consuming vast quantities of fuel per launch.
  • Use mostly existing technologies instead of relying on the breakthrough invention of radically new materials and/or technologies.
  • Leverage the existing natural terrain when building the very large support superstructure of the launch tube, verses other extreme resource intensive designs such as entire man made mountains.
Colonizing space has been the mainstay of science fiction for decades.  One of the principal barriers to widespread space development is the cost of launching material into space.  This plan is achievable using mostly existing technology and even within the cost budgets of many nations.  It is exciting to think that mankind's push into space is getting closer to reality every day.


Relevant links:

https://en.wikipedia.org/wiki/Space_elevator

https://en.wikipedia.org/wiki/Launch_loop

https://www.youtube.com/watch?v=yrc632oilWo

Saw this months after I first posted this..

https://www.youtube.com/watch?v=Rb6sxy3f7VE

Sunday, December 13, 2020

My YouTube Channel

Here is a link to my YouTube channel where I occasionally post a video.

https://www.youtube.com/channel/UCA5OE-6UEy1FO5Xgn949ODw


I also like looking at live feeds on YouTube.

You can find them by searching on 'live streaming feeds' or similar on YouTube.


Monday, November 16, 2020

Parallel Computer Architecture: Efficient Micro Parallel Synchronization Mechanisms

I have often wondered why modern computer instruction set architectures do not have more efficient parallel synchronization mechanisms.  Current mainstream microprocessor designs currently support two types of parallelism.

  • Very fine grain
    • Hardware based implicit instruction level
    • Implemented via advanced pipeline register renaming.
    • Synchronization delays on the order of a single cycle.
  • Very course grain
    • Software based explicit thread synchronization primitives
    • Implemented via atomic memory instructions.
    • Synchronization delays on the order of tens of thousands of cycles or more.
With CPU clock frequencies beginning to plateau it may be time to revisit architectural synchronization models as a method to continue improving overall program performance.  If we have any bright PHD candidates reading this fishing for a dissertation topic, please consider this.

Parallel Architecture Models

At the process level we have the architectural notion of an interrupt.  But at the thread level this does not exist.  We have to rely on threads spinning in a loop reading and writing a shared memory location together with memory synchronization barriers and no architectural specification about how long this can take.  This is ridiculous.  We can't have efficient parallel programming if the programming model has no mechanism to facilitate it.  We need some data queue or message passing mechanism or interrupt that operates at the instruction architecture level if we are to enable efficient parallel programming.

Explicit Instruction Level Parallelism

I would like to see an efficient software visible instruction level synchronization mechanism.  For example, something like a 'Queue Register'.  Some existing IO registers track read and write state.  I'm thinking some general purpose registers could similarly be architected for managing data flow synchronization at the register data level.  Such registers could essentially stall the execution pipeline on reads until a write to that register has occurred.  So the register effectively acts as a 'data queue' at the instruction execution level.  This would enable software control of fine grain parallelism, opening up potentially more real parallelism than relying on hardware to extract parallelism from an inherently sequential programming model.

Since all compute state needs to be visible in order to stop, save, and later restart a process, status bits will also need to track the read/write data state of each queue register.  CPU pipelines could be redesigned to key off of these explicit reg data states, instead of implicit internal hardware states.  Just like current hardware threads swap in whichever thread has data ready, these new threads could work the same way.  The primary difference being the data ready state is now software architecturally visible.

Further note that these hardware queue registers are effectively thread state ready registers, analogous to ready state flags in operating system thread schedulers.  Since these ready flags are intended for micro data level parallelism, they should be closely aligned to the real register thread state supported by the hardware, as opposed to some arbitrary virtual state that relies on time slicing and swapping threads in and out of hardware.  While time slicing is theoretically possible it would blow up performance by 10000 times, entirely defeating the advantage of micro level parallelism.

So there is a different mind set when programming this level of parallelism.  This type of parallelism should have some awareness of the number of hardware threads efficiently supported by hardware, as opposed to some very course grain parallelism that has little concern about real hardware thread counts.  The implication is that this level of coding is more appropriate for hand coded assembly or for compilers.
 
References

https://riscv.org/community/directory-of-working-groups/

https://en.wikipedia.org/wiki/MIMD

https://en.wikipedia.org/wiki/Explicitly_parallel_instruction_computing

https://en.wikipedia.org/wiki/Parallel_programming_model

https://www.cs.utexas.edu/~trips/index.html

https://scholar.google.com/scholar?q=parallel+computer+architecture&hl=en&as_sdt=0&as_vis=1&oi=scholart

Politics: The Political Divide (Urban verses Rural)

The 2020 US presidential election is over and it looks like Joe Biden will be replacing Donald Trump as the next US president.  From what I've gathered from the talking heads on network TV and the internet there is a lot of angst about our deeply divided country.  Some even talk about doing away with the Electoral College.  

When I look at the electoral results map it is blindingly painfully obvious that conservative red districts are rural, and liberal blue districts are urban.  This makes perfect sense to me so I don't get why this is so hard for the major media talking heads to understand.  A rural farmer living on a 100 acre farm by absolute necessity has to be far more self sufficient and independent than a desk jockey living in a high rise condo in a large metropolis.  Duh.  This ain't rocket science. 

If you live on a rural farm, and someone is breaking into your house in the middle of the night, you don't hide in the closet and dial 911, you grab your gun and deal with it.  Waiting an hour for the sheriff to arrive is not an option, especially if you have family.  

When you're plowing your field and your tractor breaks down you get your toolbox and start diagnosing what is wrong.  Why ?  Because waiting a week for a repairmen is not an option for your crop schedule or your wallet.

Global warming ?  That is concerning, but more concerning right now for the working rural poor are their bleeding knuckles and what their family is going to eat tonight.

So can we please stop demonizing the working rural poor who voted for less federal bureaucracy and more job security in their lives ?  Donald Trump may be an amoral self serving narcissist, but that doesn't mean everything he says is wrong.  Let's not forget there is a reason he got elected for his first term.

And regarding the Electoral College, this is the mechanism that the framers of the constitution came up with to balance out the rural state needs with the urban population focused house of representatives.  Anyone who talks about scrapping the Electoral College without some other mechanism to represent the working rural poor is risking disenfranchising the working rural poor.  That is self serving, oppressive, and potentially grounds for civil war, so uh, probably not a good idea.

So please remember, we don't all live in high rise urban condos and have high paying jobs.

Monday, October 12, 2020

The McLaughlin Group

I miss John McLaughlin.

John McLaughlin brought together opinions from both the left and right in one show in an intelligent, informative, and entertaining fashion.  It seems every news show I watch now is hopelessly partisan and panders to one side or the other.  Listening to just one side of an issue not only impairs your judgement, it can harm your mental health and depress you.  It is literally how brain washing is done.

I notice that the show has recently rebooted on You tube with a new host.  

https://www.youtube.com/user/mclaughlingroup

This show has potential, but is not yet as good as the original.  Please keep bringing in new smart faces for both sides of current topics.  Hopefully some new leading personalities will develop.  

Make no mistake.  Both the left and right have have done plenty of evil before and will do so again if left unchecked.  If you don't present both sides of current issues, you are part of the problem, not the solution.  And if you're really cool (like John) you can even make it entertaining.