His story will inspire you.

“Google search went down for a few hours in 2002; Jeff Dean handled all the queries by hand and checked quality doubled.”- Jeff Dean Facts.

One of many Jeff Dean jokes, but you get the idea.

Google's top six engineers met in a war room in mid-2000. Google's crawling system, which indexed the Web, stopped working. Users could still enter queries, but results were five months old.

Google just signed a deal with Yahoo to power a ten-times-larger search engine. Tension rose. It was crucial. If they failed, the Yahoo agreement would likely fall through, risking bankruptcy for the firm. Their efforts could be lost.

A rangy, tall, energetic thirty-one-year-old man named Jeff dean was among those six brilliant engineers in the makeshift room. He had just left D. E. C. a couple of months ago and started his career in a relatively new firm Google, which was about to change the world. He rolled his chair over his colleague Sanjay and sat right next to him, cajoling his code like a movie director. The history started from there.

When you think of people who shaped the World Wide Web, you probably picture founders and CEOs like Larry Page and Sergey Brin, Marc Andreesen, Tim Berners-Lee, Bill Gates, and Mark Zuckerberg. They’re undoubtedly the brightest people on earth.

Under these giants, legions of anonymous coders work at keyboards to create the systems and products we use. These computer workers are irreplaceable.

Let's get to know him better.

It's possible you've never heard of Jeff Dean. He's American. Dean created many behind-the-scenes Google products. Jeff, co-founder and head of Google's deep learning research engineering team, is a popular technology, innovation, and AI keynote speaker.

While earning an MS and Ph.D. in computer science at the University of Washington, he was a teaching assistant, instructor, and research assistant. Dean joined the Compaq Computer Corporation Western Research Laboratory research team after graduating.

Jeff co-created ProfileMe and the Continuous Profiling Infrastructure for Digital at Compaq. He co-designed and implemented Swift, one of the fastest Java implementations. He was a senior technical staff member at mySimon Inc., retrieving and caching electronic commerce content.

Dean, a top young computer scientist, joined Google in mid-1999. He was always trying to maximize a computer's potential as a child.

An expert

His high school program for processing massive epidemiological data was 26 times faster than professionals'. Epi Info, in 13 languages, is used by the CDC. He worked on compilers as a computer science Ph.D. These apps make source code computer-readable.

Dean never wanted to work on compilers forever. He left Academia for Google, which had less than 20 employees. Dean helped found Google News and AdSense, which transformed the internet economy. He then addressed Google's biggest issue, scaling.

Growing Google faced a huge computing challenge. They developed PageRank in the late 1990s to return the most relevant search results. Google's popularity slowed machine deployment.

Dean solved problems, his specialty. He and fellow great programmer Sanjay Ghemawat created the Google File System, which distributed large data over thousands of cheap machines.

These two also created MapReduce, which let programmers handle massive data quantities on parallel machines. They could also add calculations to the search algorithm. A 2004 research article explained MapReduce, which became an industry sensation.

Several revolutionary inventions

Dean's other initiatives were also game-changers. BigTable, a petabyte-capable distributed data storage system, was based on Google File. The first global database, Spanner, stores data on millions of servers in dozens of data centers worldwide.

It underpins Gmail and AdWords. Google Translate co-founder Jeff Dean is surprising. He contributes heavily to Google News. Dean is Senior Fellow of Google Research and Health and leads Google AI.

Recognitions

The National Academy of Engineering elected Dean in 2009. He received the 2009 Association for Computing Machinery fellowship and the 2016 American Academy of Arts and Science fellowship. He received the 2007 ACM-SIGOPS Mark Weiser Award and the 2012 ACM-Infosys Foundation Award. Lists could continue.

A sneaky question may arrive in your mind: How much does this big brain earn? Well, most believe he is one of the highest-paid employees at Google. According to a survey, he is paid $3 million a year.

He makes espresso and chats with a small group of Googlers most mornings. Dean steams milk, another grinds, and another brews espresso. They discuss families and technology while making coffee. He thinks this little collaboration and idea-sharing keeps Google going.

“Some of us have been working together for more than 15 years,” Dean said. “We estimate that we’ve collectively made more than 20,000 cappuccinos together.”

We all know great developers and software engineers. It may inspire many.

A friend told me of an incident she found particularly irritating: a retailer where she is a frequent client, with an account and loyalty card, asked for the item's receipt.

We all know that stores collect every bit of data they can on us, including our socio-demographic profile, address, shopping habits, and everything we've ever bought, so why would they need a fading receipt? Who knows? That their consumers try to pass off other goods? It's easy to verify past transactions to see when the item was purchased.

That's it. Why require receipts? Companies send us incentives, discounts, and other marketing, yet when we need something, we have to prove we're not cheating.

Why require us to preserve data and documents when our governments and governmental institutions already have them? Why do I need to carry documents like my driver's license if the authorities can check if I have one and what state it's in once I prove my identity?

We shouldn't be required to give someone data or documents they already have. The days of waiting up with our paperwork for a stern official to inform us something is missing are over.

How can retailers still ask if you have a receipt if we've made our slow, bureaucratic, and all-powerful government sensible? Then what? The shop may not accept your return (which has a two-year window, longer than most purchase tickets last) or they may just let you replace the item.

Isn't this an anachronism in the age of CRMs, customer files that know what we ate for breakfast, and loyalty programs? If government and bureaucracies have learnt to use its own files and make life easier for the consumer, why do retailers ask for a receipt?

They're adding friction to the system. They know we can obtain a refund, use our warranty, or get our money back. But if I ask for ludicrous criteria, like keeping the purchase receipt in your wallet (wallet? another anachronism, if I leave the house with only my smartphone! ), it will dissuade some individuals and tip the scales in their favor when it comes to limiting returns. Some manager will take credit for lowering returns and collect her annual bonus. Having the wrong metrics is common in management.

To slow things down, asking for a receipt is like asking us to perform a handstand and leap 20 times on one foot. You have my information, use it to send me everything, and know everything I've bought, yet when I need a two-way service, you refuse to utilize it and require that I keep it and prove it.

Refuse as customers. If retailers want our business, they should treat us well, not just when we spend money. If I come to return a product, claim its use or warranty, or be taught how to use it, I am the same person you treated wonderfully when I bought it. Remember that, and act accordingly.

A store should use my information for everything, not just what it wants. Keep my info, but don't sell me anything.

WTF is wrong with you people?

When I was laid off as editor of my town's daily newspaper, I went silent on social media. I knew it was coming and had been quietly removing personal items each day, but the pain was intense.

I posted a day later. I didn't bad-mouth GateHouse Media but expressed my sadness at leaving the newspaper industry, pride in my accomplishments, and hope for success in another industry.

Normal job-loss response.

What do you recognize as abnormal?

The bullshit I’ve been reading from laid-off folks on LinkedIn.

If you're there, you know. Many Twitter or Facebook/Meta employees recently lost their jobs.

Well, many of them did not “lose their job,” actually. They were “impacted by the layoffs” at their former employer. I keep seeing that phrase.

Why don’t they want to actually say it? Why the euphemism?

Many are excited about the opportunities ahead. The jobless deny being sad.

They're ecstatic! They have big plans.

Hope so. Sincerely! Being laid off stinks, especially if, like me, your skills are obsolete. It's worse if, like me, you're too old to start a new career. Ageism exists despite denials.

Nowadays, professionalism seems to demand psychotic levels of fake optimism.

Why? Life is unpredictable. That's indisputable. You shouldn't constantly complain or cry in public, but you also shouldn't pretend everything's great.

It makes you look psychotic, not positive. It's like saying at work:

“I was impacted by the death of my spouse of 20 years this week, and many of you have reached out to me, expressing your sympathy. However, I’m choosing to remember the amazing things we shared. I feel confident that there is another marriage out there for me, and after taking a quiet weekend trip to reset myself, I’ll be out there looking for the next great marital adventure! #staypositive #available #opentolove

Also:

“Now looking for our next #dreamhome after our entire neighborhood was demolished by a wildfire last night. We feel so lucky to have lived near so many amazing and inspirational neighbors, all of whom we will miss as we go on our next housing adventure. The best house for us is yet to come! If you have a great neighborhood you’d recommend, please feel free to reach out and touch base with us! #newhouse #newneighborhood #newlife

Admit it. That’s creepy.

The constant optimism makes me feel sick to my stomach.

Viscerally.

I hate fakes.

Imagine a fake wood grain desk. Wouldn't it be better if the designer accepted that it's plastic and went with that?

Real is better but not always nice. When something isn't nice, you don't have to go into detail, but you also shouldn't pretend it's great.

How to announce your job loss to the world.

Do not pretend to be happy, but don't cry and drink vodka all afternoon.

Say you loved your job, and that you're looking for new opportunities.

Yes, if you'll miss your coworkers. Otherwise, don't badmouth. No bridge-burning!

Please specify the job you want. You may want to pivot.

Alternatively, try this.

You could always flame out.

If you've pushed yourself too far into toxic positivity, you may be ready to burn it all down. If so, make it worthwhile by writing something like this:

Well, I was shitcanned by the losers at #Acme today. That bitch Linda in HR threw me under the bus just because she saw that one of my “friends” tagged me in some beach pics on social media after I called in sick with Covid. The good thing is I will no longer have to watch my ass around that #asspincher Ron in accounting, but I’m sad that I will no longer have a cushy job with high pay or access to the primo office supplies I’ve been sneaking home for the last five years. (Those gel pens were the best!) I am going to be taking some time off to enjoy my unemployment and hammer down shots of Jägermeister but in about five months I’ll be looking for anything easy with high pay and great benefits. Reach out if you can help! #officesupplies #unemploymentrocks #drinkinglikeagirlboss #acmesucks

It beats the fake positivity.

Deep learning-based generative art is being researched. As usual, self-learning is better. Some models, like OpenAI's DALL-E 2, require registration and can only be used online, but others can be used locally, which is usually more enjoyable for curious users. I'll demonstrate the Stable Diffusion model's operation on a standard PC.

Let’s get started.

What It Does

Stable Diffusion uses numerous components:

• A generative model trained to produce images is called a diffusion model. The model is incrementally improving the starting data, which is only random noise. The model has an image, and while it is being trained, the reversed process is being used to add noise to the image. Being able to reverse this procedure and create images from noise is where the true magic is (more details and samples can be found in the paper).

• An internal compressed representation of a latent diffusion model, which may be altered to produce the desired images, is used (more details can be found in the paper). The capacity to fine-tune the generation process is essential because producing pictures at random is not very attractive (as we can see, for instance, in Generative Adversarial Networks).

• A neural network model called CLIP (Contrastive Language-Image Pre-training) is used to translate natural language prompts into vector representations. This model, which was trained on 400,000,000 image-text pairs, enables the transformation of a text prompt into a latent space for the diffusion model in the scenario of stable diffusion (more details in that paper).

This figure shows all data flow:

The weights file size for Stable Diffusion model v1 is 4 GB and v2 is 5 GB, making the model quite huge. The v1 model was trained on 256x256 and 512x512 LAION-5B pictures on a 4,000 GPU cluster using over 150.000 NVIDIA A100 GPU hours. The open-source pre-trained model is helpful for us. And we will.

Install

Before utilizing the Python sources for Stable Diffusion v1 on GitHub, we must install Miniconda (assuming Git and Python are already installed):

wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.12.0-Linux-x86_64.sh
chmod +x Miniconda3-py39_4.12.0-Linux-x86_64.sh
./Miniconda3-py39_4.12.0-Linux-x86_64.sh
conda update -n base -c defaults conda

Install the source and prepare the environment:

git clone https://github.com/CompVis/stable-diffusion
cd stable-diffusion
conda env create -f environment.yaml
conda activate ldm
pip3 install transformers --upgrade

Download the pre-trained model weights next. HiggingFace has the newest checkpoint sd-v14.ckpt (a download is free but registration is required). Put the file in the project folder and have fun:

python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

Almost. The installation is complete for happy users of current GPUs with 12 GB or more VRAM. RuntimeError: CUDA out of memory will occur otherwise. Two solutions exist.

Running the optimized version

Try optimizing first. After cloning the repository and enabling the environment (as previously), we can run the command:

python3 optimizedSD/optimized_txt2img.py --prompt "hello world" --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

Stable Diffusion worked on my visual card with 8 GB RAM (alas, I did not behave well enough to get NVIDIA A100 for Christmas, so 8 GB GPU is the maximum I have;).

Running Stable Diffusion without GPU

If the GPU does not have enough RAM or is not CUDA-compatible, running the code on a CPU will be 20x slower but better than nothing. This unauthorized CPU-only branch from GitHub is easiest to obtain. We may easily edit the source code to use the latest version. It's strange that a pull request for that was made six months ago and still hasn't been approved, as the changes are simple. Readers can finish in 5 minutes:

• Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available at line 20 of ldm/models/diffusion/ddim.py ().

• Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available in line 20 of ldm/models/diffusion/plms.py ().

• Replace device=cuda in lines 38, 55, 83, and 142 of ldm/modules/encoders/modules.py with device=cuda if torch.cuda.is available(), otherwise cpu.

• Replace model.cuda() in scripts/txt2img.py line 28 and scripts/img2img.py line 43 with if torch.cuda.is available(): model.cuda ().

Run the script again.

Testing

Test the model. Text-to-image is the first choice. Test the command line example again:

python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

The slow generation takes 10 seconds on a GPU and 10 minutes on a CPU. Final image:

Hello world is dull and abstract. Try a brush-wielding hamster. Why? Because we can, and it's not as insane as Napoleon's cat. Another image:

Generating an image from a text prompt and another image is interesting. I made this picture in two minutes using the image editor (sorry, drawing wasn't my strong suit):

I can create an image from this drawing:

python3 scripts/img2img.py --prompt "A bird is sitting on a tree branch" --ckpt sd-v1-4.ckpt --init-img bird.png --strength 0.8

It was far better than my initial drawing:

I hope readers understand and experiment.

Stable Diffusion UI

Developers love the command line, but regular users may struggle. Stable Diffusion UI projects simplify image generation and installation. Simple usage:

• Unpack the ZIP after downloading it from https://github.com/cmdr2/stable-diffusion-ui/releases. Linux and Windows are compatible with Stable Diffusion UI (sorry for Mac users, but those machines are not well-suitable for heavy machine learning tasks anyway;).

• Start the script.

Done. The web browser UI makes configuring various Stable Diffusion features (upscaling, filtering, etc.) easy:

V2.1 of Stable Diffusion

I noticed the notification about releasing version 2.1 while writing this essay, and it was intriguing to test it. First, compare version 2 to version 1:

• alternative text encoding. The Contrastive LanguageImage Pre-training (CLIP) deep learning model, which was trained on a significant number of text-image pairs, is used in Stable Diffusion 1. The open-source CLIP implementation used in Stable Diffusion 2 is called OpenCLIP. It is difficult to determine whether there have been any technical advancements or if legal concerns were the main focus. However, because the training datasets for the two text encoders were different, the output results from V1 and V2 will differ for the identical text prompts.

• a new depth model that may be used to the output of image-to-image generation.

• a revolutionary upscaling technique that can quadruple the resolution of an image.

• Generally higher resolution Stable Diffusion 2 has the ability to produce both 512x512 and 768x768 pictures.

The Hugging Face website offers a free online demo of Stable Diffusion 2.1 for code testing. The process is the same as for version 1.4. Download a fresh version and activate the environment:

conda deactivate  
conda env remove -n ldm  # Use this if version 1 was previously installed
git clone https://github.com/Stability-AI/stablediffusion
cd stablediffusion
conda env create -f environment.yaml
conda activate ldm

Hugging Face offers a new weights ckpt file.

The Out of memory error prevented me from running this version on my 8 GB GPU. Version 2.1 fails on CPUs with the slow conv2d cpu not implemented for Half error (according to this GitHub issue, the CPU support for this algorithm and data type will not be added). The model can be modified from half to full precision (float16 instead of float32), however it doesn't make sense since v1 runs up to 10 minutes on the CPU and v2.1 should be much slower. The online demo results are visible. The same hamster painting with a brush prompt yielded this result:

It looks different from v1, but it functions and has a higher resolution.

The superresolution.py script can run the 4x Stable Diffusion upscaler locally (the x4-upscaler-ema.ckpt weights file should be in the same folder):

python3 scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt

This code allows the web browser UI to select the image to upscale:

The copy-paste strategy may explain why the upscaler needs a text prompt (and the Hugging Face code snippet does not have any text input as well). I got a GPU out of memory error again, although CUDA can be disabled like v1. However, processing an image for more than two hours is unlikely:

Stable Diffusion Limitations

When we use the model, it's fun to see what it can and can't do. Generative models produce abstract visuals but not photorealistic ones. This fundamentally limits The generative neural network was trained on text and image pairs, but humans have a lot of background knowledge about the world. The neural network model knows nothing. If someone asks me to draw a Chinese text, I can draw something that looks like Chinese but is actually gibberish because I never learnt it. Generative AI does too! Humans can learn new languages, but the Stable Diffusion AI model includes only language and image decoder brain components. For instance, the Stable Diffusion model will pull NO WAR banner-bearers like this:

V1:

V2.1:

The shot shows text, although the model never learned to read or write. The model's string tokenizer automatically converts letters to lowercase before generating the image, so typing NO WAR banner or no war banner is the same.

I can also ask the model to draw a gorgeous woman:

V1:

V2.1:

The first image is gorgeous but physically incorrect. A second one is better, although it has an Uncanny valley feel. BTW, v2 has a lifehack to add a negative prompt and define what we don't want on the image. Readers might try adding horrible anatomy to the gorgeous woman request.

If we ask for a cartoon attractive woman, the results are nice, but accuracy doesn't matter:

V1:

V2.1:

Another example: I ordered a model to sketch a mouse, which looks beautiful but has too many legs, ears, and fingers:

V1:

V2.1: improved but not perfect.

V1 produces a fun cartoon flying mouse if I want something more abstract:

I tried multiple times with V2.1 but only received this:

The image is OK, but the first version is closer to the request.

Stable Diffusion struggles to draw letters, fingers, etc. However, abstract images yield interesting outcomes. A rural landscape with a modern metropolis in the background turned out well:

V1:

V2.1:

Generative models help make paintings too (at least, abstract ones). I searched Google Image Search for modern art painting to see works by real artists, and this was the first image:

I typed "abstract oil painting of people dancing" and got this:

V1:

V2.1:

It's a different style, but I don't think the AI-generated graphics are worse than the human-drawn ones.

The AI model cannot think like humans. It thinks nothing. A stable diffusion model is a billion-parameter matrix trained on millions of text-image pairs. I input "robot is creating a picture with a pen" to create an image for this post. Humans understand requests immediately. I tried Stable Diffusion multiple times and got this:

This great artwork has a pen, robot, and sketch, however it was not asked. Maybe it was because the tokenizer deleted is and a words from a statement, but I tried other requests such robot painting picture with pen without success. It's harder to prompt a model than a person.

I hope Stable Diffusion's general effects are evident. Despite its limitations, it can produce beautiful photographs in some settings. Readers who want to use Stable Diffusion results should be warned. Source code examination demonstrates that Stable Diffusion images feature a concealed watermark (text StableDiffusionV1 and SDV2) encoded using the invisible-watermark Python package. It's not a secret, because the official Stable Diffusion repository's test watermark.py file contains a decoding snippet. The put watermark line in the txt2img.py source code can be removed if desired. I didn't discover this watermark on photographs made by the online Hugging Face demo. Maybe I did something incorrectly (but maybe they are just not using the txt2img script on their backend at all).

Conclusion

The Stable Diffusion model was fascinating. As I mentioned before, trying something yourself is always better than taking someone else's word, so I encourage readers to do the same (including this article as well;).

Is Generative AI a game-changer? My humble experience tells me:

• I think that place has a lot of potential. For designers and artists, generative AI can be a truly useful and innovative tool. Unfortunately, it can also pose a threat to some of them since if users can enter a text field to obtain a picture or a website logo in a matter of clicks, why would they pay more to a different party? Is it possible right now? unquestionably not yet. Images still have a very poor quality and are erroneous in minute details. And after viewing the image of the stunning woman above, models and fashion photographers may also unwind because it is highly unlikely that AI will replace them in the upcoming years.

• Today, generative AI is still in its infancy. Even 768x768 images are considered to be of a high resolution when using neural networks, which are computationally highly expensive. There isn't an AI model that can generate high-resolution photographs natively without upscaling or other methods, at least not as of the time this article was written, but it will happen eventually.

• It is still a challenge to accurately represent knowledge in neural networks (information like how many legs a cat has or the year Napoleon was born). Consequently, AI models struggle to create photorealistic photos, at least where little details are important (on the other side, when I searched Google for modern art paintings, the results are often even worse;).

• When compared to the carefully chosen images from official web pages or YouTube reviews, the average output quality of a Stable Diffusion generation process is actually less attractive because to its high degree of randomness. When using the same technique on their own, consumers will theoretically only view those images as 1% of the results.

Anyway, it's exciting to witness this area's advancement, especially because the project is open source. Google's Imagen and DALL-E 2 can also produce remarkable findings. It will be interesting to see how they progress.

Three options exist. The third one is the quickest and most fruitful.

You've mastered crypto trading and want to become a broker.

So you may wonder: Where to begin?

If so, keep reading.

Today I'll compare three different approaches to becoming a cryptocurrency trader.

What are cryptocurrency brokers, and how do they vary from stockbrokers?

A stockbroker implements clients' market orders (retail or institutional ones).

Brokerage firms are regulated, insured, and subject to regulatory monitoring.

Stockbrokers are required between buyers and sellers. They can't trade without a broker. To trade, a trader must open a broker account and deposit money. When a trader shops, he tells his broker what orders to place.

Crypto brokerage is trade intermediation with cryptocurrency.

In crypto trading, however, brokers are optional.

Crypto exchanges offer direct transactions. Open an exchange account (no broker needed) and make a deposit.

Question:

Since crypto allows DIY trading, why use a broker?

Let's compare cryptocurrency exchanges vs. brokers.

Broker versus cryptocurrency exchange

Most existing crypto exchanges are basically brokers.

Examine their primary services:

• connecting purchasers and suppliers

• having custody of clients' money (with the exception of decentralized cryptocurrency exchanges),

• clearance of transactions.

Brokerage is comparable, don't you think?

There are exceptions. I mean a few large crypto exchanges that follow the stock exchange paradigm. They outsource brokerage, custody, and clearing operations. Classic exchange setups are rare in today's bitcoin industry.

Back to our favorite “standard” crypto exchanges. All-in-one exchanges and brokers. And usually, they operate under a broker or a broker-dealer license, save for the exchanges registered somewhere in a free-trade offshore paradise. Those don’t bother with any licensing.

What’s the sense of having two brokers at a time?

Better liquidity and trading convenience.

The crypto business is compartmentalized.

We have CEXs, DEXs, hybrid exchanges, and semi-exchanges (those that aggregate liquidity but do not execute orders on their sides). All have unique regulations and act as sovereign states.

There are about 18k coins and hundreds of blockchain protocols, most of which are heterogeneous (i.e., different in design and not interoperable).

A trader must register many accounts on different exchanges, deposit funds, and manage them all concurrently to access global crypto liquidity.

It’s extremely inconvenient.

Crypto liquidity fragmentation is the largest obstacle and bottleneck blocking crypto from mass adoption.

Crypto brokers help clients solve this challenge by providing one-gate access to deep and diverse crypto liquidity from numerous exchanges and suppliers. Professionals and institutions need it.

Another killer feature of a brokerage may be allowing clients to trade crypto with fiat funds exclusively, without fiat/crypto conversion. It is essential for professional and institutional traders.

Who may work as a cryptocurrency broker?

Apparently, not anyone. Brokerage requires high-powered specialists because it involves other people's money.

Here's the essentials:

• excellent knowledge, skills, and years of trading experience

• high-quality, quick, and secure infrastructure

• highly developed team

• outstanding trading capital

• High-ROI network: long-standing, trustworthy connections with customers, exchanges, liquidity providers, payment gates, and similar entities

• outstanding marketing and commercial development skills.

What about a license for a cryptocurrency broker? Is it necessary?

Complex question.

If you plan to play in white-glove jurisdictions, you may need a license. For example, in the US, as a “money transmitter” or as a CASSP (crypto asset secondary services provider) in Australia.

Even in these jurisdictions, there are no clear, holistic crypto brokerage and licensing policies.

Your lawyer will help you decide if your crypto brokerage needs a license.

Getting a license isn't quick. Two years of patience are needed.

How can you turn into a cryptocurrency broker?

Finally, we got there! 🎉

Three actionable ways exist:

1. To kickstart a regulated stand-alone crypto broker

2. To get a crypto broker franchise, and

3. To become a liquidity network broker.

Let's examine each.

1. Opening a regulated cryptocurrency broker

It's difficult. Especially If you're targeting first-world users.

You must comply with many regulatory, technical, financial, HR, and reporting obligations to keep your organization running. Some are mentioned above.

The licensing process depends on the products you want to offer (spots or derivatives) and the geographic areas you plan to service. There are no general rules for that.

In an overgeneralized way, here are the boxes you will have to check:

• capital availability (usually a large amount of capital c is required)

• You will have to move some of your team members to the nation providing the license in order to establish an office presence there.

• the core team with the necessary professional training (especially applies to CEO, Head of Trading, Assistant to Head of Trading, etc.)

• insurance

• infrastructure that is trustworthy and secure

• adopted proper AML/KYC/financial monitoring policies, etc.

Assuming you passed, what's next?

I bet it won’t be mind-blowing for you that the license is just a part of the deal. It won't attract clients or revenue.

To bring in high-dollar clientele, you must be a killer marketer and seller. It's not easy to convince people to give you money.

You'll need to be a great business developer to form successful, long-term agreements with exchanges (ideally for no fees), liquidity providers, banks, payment gates, etc. Persuade clients.

It's a tough job, isn't it?

I expect a Quora-type question here:

Can I start an unlicensed crypto broker?

Well, there is always a workaround with crypto!

You can register your broker in a free-trade zone like Seychelles to avoid US and other markets with strong watchdogs.

This is neither wise nor sustainable.

First, such experiments are illegal.

Second, you'll have trouble attracting clients and strategic partners.

A license equals trust. That’s it.

Even a pseudo-license from Mauritius matters.

Here are this method's benefits and downsides.

Cons first.

• As you navigate this difficult and expensive legal process, you run the risk of missing out on business prospects. It's quite simple to become excellent compliance yet unable to work. Because your competitors are already courting potential customers while you are focusing all of your effort on paperwork.

• Only God knows how long it will take you to pass the break-even point when everything with the license has been completed.

• It is a money-burning business, especially in the beginning when the majority of your expenses will go toward marketing, sales, and maintaining license requirements. Make sure you have the fortitude and resources necessary to face such a difficult challenge.

Pros

• It may eventually develop into a tool for making money. Because big guys who are professionals at trading require a white-glove regulated brokerage. You have every possibility if you work hard in the areas of sales, marketing, business development, and wealth. Simply put, everything must align.

Launching a regulated crypto broker is analogous to launching a crypto exchange. It's ROUGH. Sure you can take it?

2. Franchise for Crypto Broker (Crypto Sub-Brokerage)

A broker franchise is easier and faster than becoming a regulated crypto broker. Not a traditional brokerage.

A broker franchisee, often termed a sub-broker, joins with a broker (a franchisor) to bring them new clients. Sub-brokers market a broker's products and services to clients.

Sub-brokers are the middlemen between a broker and an investor.

Why is sub-brokering easier?

• less demanding qualifications and legal complexity. All you need to do is keep a few certificates on hand (each time depends on the jurisdiction).

• No significant investment is required

• there is no demand that you be a trading member of an exchange, etc.

As a sub-broker, you can do identical duties without as many rights and certifications.

What about the crypto broker franchise?

Sub-brokers aren't common in crypto.

In most existing examples (PayBito, PCEX, etc.), franchises are offered by crypto exchanges, not brokers. Though we remember that crypto exchanges are, in fact, brokers, do we?

Similarly:

• For a commission, a franchiser crypto broker receives new leads from a crypto sub-broker.

See above for why enrolling is easy.

Finding clients is difficult. Most crypto traders prefer to buy-sell on their own or through brokers over sub-broker franchises.

3. Broker of the Crypto Trading Network (or a Network Broker)

It's the greatest approach to execute crypto brokerage, based on effort/return.

Network broker isn't an established word. I wrote it for clarity.

Remember how we called crypto liquidity fragmentation the current crypto finance paradigm's main bottleneck?

Where there's a challenge, there's progress.

Several well-funded projects are aiming to fix crypto liquidity fragmentation. Instead of launching another crypto exchange with siloed trading, the greatest minds create trading networks that aggregate crypto liquidity from desynchronized sources and enable quick, safe, and affordable cross-blockchain transactions. Each project offers a distinct option for users.

Crypto liquidity implies:

• One-account access to cryptocurrency liquidity pooled from network participants' exchanges and other liquidity sources

• compiled price feeds

• Cross-chain transactions that are quick and inexpensive, even for HFTs

• link between participants of all kinds, and

• interoperability among diverse blockchains

Fast, diversified, and cheap global crypto trading from one account.

How does a trading network help cryptocurrency brokers?

I’ll explain it, taking Yellow Network as an example.

Yellow provides decentralized Layer-3 peer-to-peer trading.

• trade across chains globally with real-time settlement and

• Between cryptocurrency exchanges, brokers, trading companies, and other sorts of network members, there is communication and the exchange of financial information.

Have you ever heard about ECN (electronic communication network)? If not, it's an automated system that automatically matches buy and sell orders. Yellow is a decentralized digital asset ECN.

Brokers can:

• Start trading right now without having to meet stringent requirements; all you need to do is integrate with Yellow Protocol and successfully complete some KYC verification.

• Access global aggregated crypto liquidity through a single point.

• B2B (Broker to Broker) liquidity channels that provide peer liquidity from other brokers. Orders from the other broker will appear in the order book of a broker who is peering with another broker on the market. It will enable a broker to broaden his offer and raise the total amount of liquidity that is available to his clients.

• Select a custodian or use non-custodial practices.

Comparing network crypto brokerage to other types:

• A licensed stand-alone brokerage business is much more difficult and time-consuming to launch than network brokerage, and

• Network brokerage, in contrast to crypto sub-brokerage, is scalable, independent, and offers limitless possibilities for revenue generation.

Yellow Network Whitepaper. has more details on how to start a brokerage business and what rewards you'll obtain.

Final thoughts

There are three ways to become a cryptocurrency broker, including the non-conventional liquidity network brokerage. The last option appears time/cost-effective.

Crypto brokerage isn't crowded yet. Act quickly to find your right place in this market.

Choose the way that works for you best and see you in crypto trading.

Discover Web3 & DeFi with Yellow Network!

Yellow, powered by Openware, is developing a cross-chain P2P liquidity aggregator to unite the crypto sector and provide global remittance services that aid people.

Join the Yellow Community and plunge into this decade's biggest product-oriented crypto project.

• Observe Yellow Twitter

• Enroll in Yellow Telegram

• Visit Yellow Discord.

• On Hacker Noon, look us up.

Yellow Network will expose development, technology, developer tools, crypto brokerage nodes software, and community liquidity mining.