Moonshot - Predicting the future and making JARVIS!

LOLLLLLL actually funnily I just asked GPT3 to complete the sentence:
“What do you think of the idea of creating a full Earth simulation to predict the future of everything?”

I think it’s a great idea, and I think the future of everything is going to be dictated by artificial intelligence, which means that we’d better know how to simulate it.

What do you envision the future of Earth-like simulation to look like?

I think it’s going to be huge. I think it’s going to be the next big thing. I think it’s going to be bigger than the internet.

How would you respond to the people who think this is a silly idea?

All of our ideas are silly to somebody. I think if you can’t understand that, then you’re probably not the type of person who’s going to be doing this.

How do you respond to people who think that everything will be fine, and you’re making a mountain out of a molehill?

I think that’s not true. I think things are not fine. I think things are terrible. I think this is one of

Yikes let’s be more civil! I’ll read your book if I have time.

AGI / Superintelligence? Yikes that’s even more more harder than what Moonshot’s aim is to do.

Well thanks for the good luck! Moonshot is my passion and so we’re trying our very best to make it work!!

I’m sorry you chose to interpret my words as uncivil. You continued to respond so I assumed the dialog remained open. Feel free to stop responding or block me at any time.

AGI is far closer than a total world simulation, certainly closer than one with any utility value or accuracy. That’s simply a mathematical truth. As far as your credentials, I didn’t attack something you do not possess. I’m merely asking the same pointed questions you can expect from future investors. It is merely a fact that you do not possess the knowledge or experience to create an entire world simulation. In point of fact, no one does.

What makes you think you can invent something so astounding on your own? Isaac Asimov imagined such a simulation in the Foundation series and it’s so farfetched that no one has even attempted it, so far as I know.

I was hoping to recruit someone of your talents.

Yes I agree a full full Earth simulation is extremely hard, nearly on the impossible spectrum. But it’s possible right? Obviously predicting weather, climate, earthquakes, volcanic eruptions, nature, population movements, everything sounds crazy. I totally agree.

In fact it might even be computationally intractable. According to studies, 1 Trillion living organisms are on Earth. Clearly simulating everything is crazy.

But Moonshot’s mission is 50 years. I know we can’t make it in 2021. Hence why Moonshot’s first aim is market crashes, economic sentiment then life expectancy, health outcomes, then rising sea levels, air pollution, fire, flood risks, then we’ll branch out.

Surely you don’t mean to suggest that the above topics I listed as “unpredictable?”

In terms of credentials, I’m not sure if I’m qualified to do any anything related to predicting the future, but I previously helped the Australian government model Zika Virus outbreaks months ahead; helped Australian authorities model traffic congestion and transport usage; helped authorities model air pollution and health risks on transport; helped predict domestic violence based from social media; helped predict car crash incidences for insurance companies; advised companies on how to use ML to reduce energy usage, make autonomous scanning robots, and recommend the best tasks / content to people; taught 100+ students on machine learning over 20 weeks during uni; taught 50+ PhD / Masters students as lab lecturer about data science; previously at NVIDIA making algos on GPUs faster; part of Australia’s national Environmental Sciences Olympiad team; made algos faster (Hyperlearn) with researchers from Greece, UW using methods, and methods incorportated into Pytorch, Scipy, GCC.

I highly highly disagree AGI is closer than an Earth sim. That’s categorically totally incorrect. An AGI needs to be able to predict future events and simulate Earth events, otherwise how is it an AGI / ASI??? You ask it a question “how will rising sea levels affect my property price?” or “how long will I live?” or “how will local air pollution impact my lifespan?” Will the suppos-ed AGI / ASI answer these questions?

Hi I am actually qurious how you have optimized the algorithm for nvdia faster.
I am trying to optimize time effectivenes on all levels.

I believe its a very good feeling to crack the time

2 Likes

Hi @cagri!!! Oh yay you’re interested in fast algos!! :slight_smile: Ye optimizing algos on every level is super important, since the benefits multiply!!

Yes yes YES!!! It’s such a GOOODDD feeling when you see a 3 hour algorithm run in under 5 seconds!!

So I contributed to many parts when I was back at NVIDIA:

  1. TSNE on GPUs run now in 5 seconds instead of 3 hours. Accelerating TSNE with GPUs: From hours to seconds | by Daniel Han-Chen | RAPIDS AI | Medium
  2. Makes SVD use less memory on GPUs. Make SVD overwrite temporary array x by danielhanchen · Pull Request #2277 · cupy/cupy · GitHub
  3. In the backend, contributed to NMF, Randomized SVD, focusing on making TSNE not just fit_predict, but work on new data, helped on linear algebra methods, faster kernels for data visualization algos etc.

The main takeaways are:

Re-read / re-study the algorithm your trying to optimize.

  1. Example linear regression theta = np.linalg.lstsq(X, y) can be written in maths as theta = np.linalg.inv(X.T @ X) @ X.T @ y. You can either use QR decomposition, SVD or Eigendecomposition. Ie theta = V * S @ U.T @ y or theta = R^-1 @ Q.T @ y or theta = V * E^-1 @ V.T @ X.T @ y. But the best is using Cholesky.
  2. First reduce FLOPS by BRACKETING correctly. theta = np.linalg.inv(X.T @ X) @ (X.T @ y).
  3. Reduce FLOPS by noticing X.T @ X is a symmetric matrix via BLAS. theta = np.linalg.inv(ssyrk(X)) @ (X.T @ y)
  4. Reduce FLOPS by using LDL Decomposition Inverse theta = LDL_inverse(ssyrk(X)) @ (X.T @ y)
  5. Reduce FLOPS by using perturbed Cholesky inverse theta = Chol_inverse(ssyrk(X)) @ (X.T @ y)
  6. Reduce FLOPS by using perturbed Cholesky solve theta = Chol_solve(ssyrk(X), (X.T @ y))

The final step reduces complexity dramatically. SVD takes O(np^2) time, but the constants are generally huge say 15 * np^2. On the other hand step 6 has around 2p^3 + 2p^2 + np^2 + np time. In other words, approximately 10 or so times faster.

It gets better. If you use randomized algorithms, u chop the matrix dimensions to log(n)p so you get around 2p^3 + 2p^2 + log(n)p^2 + 2np time.

2 Likes

I appricated your response so much.
Thank you .
I wish you the best of every good thing

2 Likes

Thanks a bunch @cagri !!! Super duper appreciate it!! :slight_smile:

2 Likes

GTP3 + doesn’t care about Disney licenses,

1 Like

Lol I was just recently trying to slowly minus JARVIS from whenever I was talking about Moonshot.

It has already been hardcoded in, don’t waste your time with naming conventions, check out ie compare and contrast w\ GitHub - NVIDIA/Megatron-LM: Ongoing research training transformer language models at scale, including: BERT & GPT-2
| GitHub - microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

1 Like

Blockquote https://www.microsoft.com/en-us/research/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/

1 Like

:slight_smile: ! Yay! Ye Microsoft + NVIDIA’s continual use of Megatron (Hasbro trademarked it), or like BERT, ELMO etc etc seem fine!

But ye thanks for that @YT ! :slight_smile: Definitely will be keeping JARVIS! :slight_smile: Plus we’re probably doing free advertisement for Disney!

2 Likes

Nope. JARVIS Trademark of Marvel Characters, Inc. - Registration Number 4737881 - Serial Number 86294162 :: Justia Trademarks

Computer application software that may be downloaded via global computer networks and electronic communication networks for use in connection with mobile computers, mobile phones, and tablet computers, namely, software for use as a voice controlled personal digital assistant

You will run afoul of the most powerful media conglomerate of the world if you keep JARVIS. Trust me, I already looked into it. Disney has no qualms about suing anyone and everyone.

You don’t need to delete your posts… I’m not offended by ur constructive criticism. I was just saying ur way of writing was a bit off-putting.

Sorry I missed this. Yes, those topics are largely unpredictable with any level of accuracy. Furthermore, the world is not just an algorithm to be optimized.

I think you might have miscontrued what I was saying. Yes I agree weather, volcanic eruptions, large large large natural systems are “quite unpredictable”. In fact, vast arrays of studies show this to be the case. Chaos rules, and the butterfly effect is extremely problematic when small initial conditions change. HOWEVER, recent advances in fluid dynamics modelling will solve some of these issues. DMD (Dynamic Mode Decomposition see https://youtu.be/sQvrK8AGCAo) was used extensively for fluid dynamics, climate change modelling, mouse brain modelling and so on. The new ODE45 intertwined with MLPs seem fascinating (see https://youtu.be/jltgNGt8Lpg). Likewise Multiscale predictions (see https://youtu.be/Jfl3dIlSTrU)

I once again AGREE with you that large scale natural systems are very very very very very hard to predict.

In all cases, you had high quality data handed to you. The real world is messy.

Oh no nononooo. The data was MESSY AS HELL!!! We had to predict rainfall patterns in Pakistan in collaboration with UNSW researchers, since large downpours caused flash flooding causing death. The data was ATTROCIOUS! People accidentally put data in the WRONG columns, averaged the results up wrong, whole swathes of data from regions were wrong, data averaging across time didn’t match with the averages the people gave etc. It was a nightmare.

Predicting Zika Virus outbreaks in collab with the National Health Medical Research Council and EpiWatch was also very nightmarish. Data exists yes, for cases of Zika. But the issue was to predict the ONSET of an outbreak. So what data do we use? We used Google Trends in multiple languages for every state in Brazil. But it was still very weak. So we had to devise a new model entirely from scratch called the Markovian SIRD model, where we took into account transport links, airplane routes, road links, population, mosquito population distributions, temperature, humidity, etc.

That’s an arbitrary definition that you just invented. The definition of AGI is that it “can perform any intellectual task that any human can”. Can humans predict the future with extreme accuracy? No they cannot. You’ve arbitrarily set the goalpost for AGI to something that is literally impossible. Humans can, however, predict the future based on passed experience. We do this all the time when we predict what word someone is going to type ____. Did you guess “next”?

Ok I agree. I accidentally conflated AGI and ASI. Superintelligence might not even be able to answer future prediction questions, although I would really want it to. AGI fine, using a baseline definition, AGI should do everything a human can do intelluctually (let’s discount physical movements for now). I would even say an AGI should just do 51% better than the AVERAGE human, and I would be happy. Yes I agree a basic AGI system based on say the Mixture of Experts approach should be able to exist in the next few years. It seems reasonable.

Yes, it sounds like we agree. I just dont understand why youre wasting your time and talent on this problem then. Dont you think that tech giants like IBM, Amazon, and Microsoft would be working on this problem with considerably more resources than you?

Because it’s what makes me not sleep at night!!! I LOVE what I do? Is that a good enough reason? I super extremely just super duper love what I do everyday, and I’m just happy I’m trying to make a good difference to the world. The financial predictions - I agree competition is rife. But so? My family is damn waiting for me to manage their funds. Likewise, life expectancy, disease, flood, fire risks, house prices, heart disease etc prevalance - these might exist ok yes. But once again - I’m waiting to use it. I want to know how long I live. I want to know how to improve optimally. I want to know what factors I need to look out for. My family has a long history of hypertension, stomach cancer and my grandparents siblings have alzhemiers. I want to know how to live longer. Don’t we all?

At the end of the day, I understand fully and I agree with you - “but isn’t OpenAI, Microsoft, Deepmind, governments from the US, China doing this?” Yes I had that mantra before. But it doesn’t faze me. Even if other large corporations will attempt it, I’m sure what Moonshot does will help the world. Even if we’re stamped and trampled on, I want to do what’s right for the world, and not regret any decision I make when I die. I believe that we’re aiming for the stars, and it’ll be tough - super tough. But I want to press on!!!

Anyways thanks though @daveshapautomator for ur precious time. I wholeheartedly thank you for actually making you write a lot, and I appreciate it. Obvisously some rephrasement might be necessary, but in general your criticism is just and reasonable.

Yikes I wrote too much.

Homegrown ai will out preform in other sectors of wellbeing, and so far all of them work hand in hand, the good ones at least, so keep up the homegrown work @danielhanchen , I’ll be routing your Jarvis some day,

1 Like

Thanks @YT !!! Super appreciate your support and thanks so much!! I really hope Moonshot will help make the world a better place!!

Yess!! When a basic JARVIS version comes out, I’ll post it here!! :slight_smile:

1 Like

Well, I completely understand intense passion. There were many days that I woke up at 4am to work on my AGI and write my book. And it wasn’t by choice either. Carry on.

FYI I was under the impression that you were trying to start a business, hence my pointed questions. That was the source of disconnect.

1 Like

Your questions are fine in terms of content. Possibly I over-interpreted / over-analysed the exact underpinnings of ur phrasing.

But anyways once again I’ll defs try reading your book! You’ll have to give me some time though since it’s been real hectic recently!

Ye in the business world, competition is rife. If I can’t take pointed questions, then I guess I deserve to be culled :slight_smile: Definitely you made me stronger and more resilient - so once again thanks @daveshapautomator !

1 Like

My brother made a delicious stunning website for Moonshot!!!
www.moonshotai.org

We’re planning to probably get a better domain, but for now it’ll do!

Any suggestions are welcome!! The site is still under HEAVY construction, so buttons won’t work, pages are blank / still being filled etc!

A small snapshot of the site!

3 Likes