Monthly Archives: July 2024

Can AI understand webcomics?

Vision language models (VLMs) are a new type of artificial intelligence that combines computer vision with the natural language processing capabilities of large language models. VLMs are often capable of chatting but they are designed to particularly excel in understanding and generating text about images.

Over the past several months, many VLMs have been released including open source ones that can be run locally on home computers. In this post, I will be testing their capabilities using this webcomic:

Based on the original “Illusion” webcomic by Abstruse Goose (CC BY-NC 3.0 US).

Here is the prompt that I used:

What is the message being conveyed by this image?

And here are the results:

Chameleon:

The image is a cartoon-style diagram that depicts a simple flowchart. The main subject is a sheep, which is depicted as a black outline with a white body. The sheep is situated in the center of the image and faces to the left. The flowchart itself is drawn on a white background and features three main branches, each of which is labeled with a word or phrase. The branches originate from a central node labeled "This is a flowchart." The leftmost branch is labeled "Chickens," while the middle branch is labeled "Foxes." The rightmost branch is labeled "Flies." Each branch then splits into smaller sub-branches, which are labeled with additional words or phrases. The leftmost branch has two sub-branches: "Lay eggs" and "Get eaten." The middle branch has three sub-branches: "Catch mice," "Catch rabbits," and "Get eaten." The rightmost branch has two sub-branches: "Bite humans," and "Get eaten." Each sub-branch ends in a small circle or oval, which adds a sense of finality to the flow

ChartGemma:

The image is a satirical depiction of the illusion of free choice, highlighting the potential limitations of democratic systems.

Idefics2-8B:

There are two cows, one on each side of a wall. The cow on the left represents Democrats and the cow on the right represents Republicans. They both want to get to the "Slaughter House" but there's a big obstacle in their way. This illustrates how both parties work together for their own interests instead of working together as a whole.

Idefics2-8B-chatty:

The message being conveyed by this image is that there are limited options or choices available for both Democrats and Republicans, which can be seen as a metaphorical representation of the political landscape in the United States. The cow standing at the bottom of the image symbolizes the American people who are often faced with only two main political parties to choose from when voting. This limited choice can lead to a sense of frustration or dissatisfaction among voters, as they may feel that their preferences and concerns are not fully represented by either party.

The image also highlights the idea that both Democrats and Republicans might have some similarities or shared beliefs, despite their differences. This can be seen through the fact that they are both standing on the same side of the wall, suggesting that they share common ground or goals. However, the wall itself represents the division between these two groups, emphasizing the polarization and partisanship that often characterize American politics.

In conclusion, the image of the cow standing below the two political parties and the wall between them serves as a reminder of the limited choices and the division that exists within the American political system, while also hinting at potential areas of agreement or commonality between the two major parties.

LLaVA 1.5:

The image conveys a message about the concept of "free choice" and the illusion of it. It features a cow standing in front of a sign that says "Slaughter House" and another sign that says "Republicans." The cow is looking at the signs, which suggests that it is aware of its situation and the potential consequences of its actions. The image might be suggesting that even though the cow has the freedom to choose, its choices are ultimately limited by its environment and the decisions made by others. This can be interpreted as a commentary on the limitations of free choice in certain situations or the influence of external factors on individual decision-making.

OpenGPT 4o:

The image is a cartoon that illustrates a political divide between Democrats and Republicans. It features a cow standing in the middle of a road with a sign that reads "SLAUGHTER HOUSE" on one side and "THE ILLUSION OF FREE CHOICE" on the other. The cow appears to be looking at the sign on the "SLAUGHTER HOUSE" side, which suggests that the cow is being influenced by the illusion of free choice on that side. The message being conveyed is that the illusion of free choice can be misleading and that the true power in politics is held by those who control the "SLAUGHTER HOUSE," which is a metaphor for the concentration of power in the hands of a small elite.

In order to make things a bit more challenging for the AI, I then repeated the same experiment but with the explanation text removed:

The edited version with explanation text removed.

Here are the results of that second experiment:

Chameleon:

This image is conveying a message that when you make a big change, it can cause a lot of pain and discomfort, but in the long run, it will lead to great rewards.

Chameleon (another attempt):

The image is a cartoon illustration that shows three different types of borders and their purpose. The illustration is accompanied by a text that reads "Borders serve a purpose". The illustration is a clear representation of how borders help define and protect different areas or entities.

ChartGemma:

The image suggests that Republicans are moving further apart from Democrats, while Democrats are moving further apart from Republicans.

Idefics2-8B:

This cartoon shows a cow looking at two doors. One door has "Democrats" written on it and the other one has "Republicans." The cow represents the American people who are trying to decide which party they want to vote for in an election.

Idefics2-8B-chatty:

The message being conveyed by this image is that there are two distinct groups of people or political parties - Democrats and Republicans - who have different opinions and beliefs. These differences are symbolized by the cow standing in front of the two separate walls, representing the divide between these groups. The cow looking at the wall of the "Slaughter House" suggests that the Democrats might feel threatened or endangered by the actions or policies of the Republicans, while the cow looking at the wall of the "Republicans" indicates that the Republicans may also have concerns or disagreements with the Democrats. Overall, the image highlights the polarization and division within politics, where opposing viewpoints often lead to conflict and tension.

LLaVA 1.5:

The image conveys a message about the political divide in the United States, specifically between Democrats and Republicans. The cow is standing in front of two doors, each labeled with the name of a political party. The cow represents a neutral observer, and the doors symbolize the two opposing political parties. The image suggests that the political divide is as deep as the ocean, with no easy way to bridge the gap between the two parties. This can be interpreted as a commentary on the challenges faced in achieving consensus and cooperation between the two parties in the political arena.

OpenGPT 4o:

The image is a cartoon that illustrates a humorous take on the political divide in the United States. It features a cow standing in the middle of a road with two signs on either side, labeled "Democrats" and " Republicans". The cow appears to be facing the "Democrats" sign, but is facing away from the " Republicans" sign. This could be interpreted as a commentary on how people may be more interested in the policies or ideas of the party they align with, rather than the party itself. The image is not meant to be taken seriously and is likely intended as a light-hearted joke.

As you can see, any perceived understanding immediately falls apart once the explanation text is removed. And even when it isn’t, there is still room for improvement. Some models identified the cow as a sheep, while others identified two cows when there is only one. Chameleon in particular seems to be quite prone to hallucinating. Given that it’s actually one of the more recent models, I’m not sure why it did so badly.

If you know of any other non-paid models that I could test for this experiment then feel free to post them in the comments. As the technology improves, I’m sure better VLMs will be released in the future that will easily pass this test. Until then, it’s probably fair to say that the answer to the question posed by this post’s title is “no” – i.e. current AIs aren’t quite intelligent enough to understand webcomics yet.

Alexology now has its own chat room (well, sort of)

I’ve been meaning to add a chat room to this blog for a long time in order to enable real-time communication between me and my readers. Ideally, it would be decentralized, censorship-resistant, and accessible via Tor while still providing users with the ability to filter out messages that they don’t want to see. Some kind of way to prevent scammers from impersonating me without having to post my public PGP key every time I write a response would also be a welcome addition. Unfortunately, these requirements greatly limit my options.

There’s a very interesting project called Chitchatter which ticks some of these boxes. It’s open source, decentralized, peer-to-peer, and censorship-resistant. There is no account registration – anyone can connect with anyone else by simply specifying a previously agreed-upon URL (for public chat rooms) or a URL and password (for private chat rooms). For example, here is a chat room that I “created” for this website:

https://chitchatter.im/public/alexology

(Second/alternative room: https://chitchatter.im/public/Alexology)

Unfortunately, it uses WebRTC which isn’t supported by Tor. It also allocates usernames randomly and has no way for users to filter out spammers and trolls – if a chat room becomes inundated with spambots for example then its creator advises you to pack up everything, move to a new URL, and hope that the spambots stay one step behind. Since there’s no way to prove who is who, if someone there claims to be me then you should automatically assume that they are an imposter.

There’s another chat room on the dark web called Ableonion (link requires Tor Browser to access). I find its way of doing things to be quite neat. There is a CAPTCHA which presumably filters out most bots but some still get through. Instead of relying on a centralized moderation team however, you can choose to mute anyone (or any bot) that you don’t want to see by simply entering /ignore in the text field followed by a space and then their username which will make all of their previous and future messages disappear from your view.

If you know of any other options that fulfill these requirements then feel free to share them in the comments. Until I can find something better, this will remain as the “official” unofficial chat room for Alexology – just don’t forget the aforementioned warning in bold.

Turn (almost) any article into a podcast with Podcastify

I was browsing through the many spaces on Hugging Face recently and found this interesting one that claims to be able to convert any text-based article into a simulated podcast featuring two AI speakers who take turns speaking.

It uses a range of open source technologies including Jina AI’s Reader for parsing URL queries to AI-friendly text, the large language model Hermes-2-Pro-Llama-3-8B by Nous Research for function calling support, and the multilingual text-to-speech library MeloTTS by MyShell to generate the actual voices.

At first I tried pasting in the Wikipedia article for AI but that brought up an error. Sensing that perhaps length could be the issue, I tried the same with the much shorter Simple English version but still got the same error. But trying a third time with an earlier article I wrote for this blog about generative AI ended up working!

Here is the result of that experiment (unlike a normal podcast, it’s only 80 seconds long).

As you can see, it’s not perfect. The voices are still somewhat robotic-sounding and some of the pronunciations are wrong. But it’s still a very interesting technology. I can see tools like this being useful for those who don’t want to read through pages upon pages of text but would rather get the gist of a subject while waiting in traffic or riding the bus, etc. That being said, a big part of the appeal of podcasts is that they’re actually entertaining to listen to, and I don’t think this AI is quite there yet.

And finally, after this post has been published, I will ask Podcastify to generate a new podcast episode based on it – making this the world’s first self-referential podcast episode!

By selling their bitcoins, the German government has made a big mistake

The German government’s Bitcoin holdings on Arkham Intelligence.

Apparently this week the German government has just finished selling off their Bitcoin stash of nearly 50,000 BTC for almost $3 billion. This along with Trump’s surge in the polls after Biden’s disastrous debate performance, his failed assassination attempt, and VP pick is probably part of the reason why Bitcoin prices are starting to come back up again after being stuck at around $57,000 for days.

Now, a lot of Bitcoiners will agree with me that this was an incredibly short-sighted decision. By selling their bitcoins for fiat, governments are trading a scarce asset enforced by mathematics and cryptography that has the potential to be the future world’s reserve currency for a bunch of paper that they could print themselves at will. Only 21 million bitcoins can ever be created versus a potentially unlimited amount of dollars or euros or renminbi, which is why you often see charts like this (click to expand):

Since 1914, the US dollar has lost 97% of its value.

In fact, governments continue to hoard gold reserves decades after abandoning the gold standard but Bitcoin still seems to go over their heads. Perhaps this shouldn’t be surprising considering that the average age of a politician in the Western world is close to 60. Or perhaps they don’t care because the coins were “seized” (a.k.a. stolen) by government thugs rather than being earned with hard work like the rest of us and were thus obtained for free.

So far, the El Salvadorian government seems to be the only government that is acting in its own self-interest. They have been accumulating BTC at a steady rate since 2021, have weathered the storms, and are now completely in the green:

The El Salvadorian government’s Bitcoin address on mempool.space.

In the German Bundestag, only MP Joana Cotar seems to realize that might have been better for their government to hold onto its bitcoins. Cotar reflected, “I can only speculate as to why the government is selling right now. As we have massive budget shortfalls in Germany at the moment, that could be one of the reasons. The upcoming elections may also play a role.”

She added, “We need to diversify our treasury and finally see and hold bitcoin as a strategic reserve currency. It is really frustrating to have to watch politicians who have no idea about the matter squander a great opportunity.”

Not that I’m complaining though. Governments selling cryptocurrencies distributes wealth to the people – the good kind of wealth that can’t be inflated and confiscated at will.

In 2014, the US government sold 30,000 bitcoins for $19 million at a price of $630 per coin. Had they waited until now, that stash would be worth $1.8 billion. In 1999, the UK government sold half of its gold reserves for $3.5 billion. Today it would be worth over $30 billion. In 10 years, the German government will probably look back at its decision to sell its bitcoins and realize that it had made the same short-sighted mistake.

Looking for a mobile generative AI workstation on a budget? Consider buying an old gaming laptop

This gaming laptop from 2017 has more VRAM (8 GB) and storage (512 GB + 1 TB) than most current laptops.

If you’re interested in running text-to-image models and large language models locally but buying a desktop isn’t an option then consider purchasing a used gaming laptop instead.

The newer RTX 20, 30, and 40 series GPUs are great cards that provide big performance boosts for games that take advantage of their newer features such as hardware ray tracing (in fact, the “R” in “RTX” stands for ray tracing) and DLSS. If you intend to play recent games at medium to high settings with high FPS, then by all means go for these modern cards.

But when it comes to AI, VRAM is king, and newer GPUs by Nvidia have been very lacking in the VRAM department. Basically, the AI boom caused Nvidia to become extremely stingy with the amount of VRAM that they put in their consumer products because they don’t want to cannibalize sales of their much more profitable enterprise products designed for corporate clients and data centers.

Case in point, the mobile GTX 1070 and RTX 4070 were mid-range cards released in 2016 and 2023 respectively. Yet, they both have the same amount of VRAM – 8 GB. If you want more VRAM in a portable form factor, Nvidia forces you to splurge on the much more expensive mobile RTX 4080 or 4090. And until AMD can prove itself to be a viable competitor in the mobile space, this situation is unlikely to improve.

Storage is another reason why these older laptops are great for AI tasks. As laptops switched from having both a hard drive and a solid state drive (SSD) to having just an SSD, their storage capacities actually decreased. Most gaming laptops from 2016 to 2019 should be fitted with both an SSD and a mechanical hard drive. The idea was that you would have your operating system and commonly used applications installed on the SSD while things like your photos, videos, music, and documents that don’t benefit from the speed advantages of the SSD can be stored on the hard drive where storage is slower but cheap and plentiful.

For generative AI, any applications you run will likewise be limited by the GPU rather than the speed of the hard drive so the performance benefits of the SSD would be wasted. Furthermore, you will most likely need to keep large amounts of datasets and media files on hand which will benefit from large amounts of cheap storage space where speed does not matter.

And finally, if you’re wondering whether the new laptops marketed with “AI” branding are any better for generative AI then unfortunately, they’re not. Compared to GPUs, the neural processing units (NPUs) inside these laptops are still fairly useless for generative AI tasks. A decent NPU might achieve 40 trillion operations per second (TOPS) while a dedicated GPU can achieve hundreds of TOPS to over 1,200 TOPS depending on the model. Instead, these NPUs are designed to assist in office tasks that might benefit from a light sprinkling of AI such as face detection and reducing background noise during video and voice calls while consuming very little energy in the process and thus reserving the GPU for more demanding tasks.

Depending on where you live, you should be able to score a gaming laptop from 2016 to 2019 for about $250-500 in the second-hand market. Try to aim for at least 16 GB RAM with a 256 GB SSD and a 1 TB mechanical hard drive. The CPU is unlikely to be a bottleneck because gaming laptops are unlikely to be fitted with crappy Celerons and pre-Ryzen AMD APUs. That being said, try to aim for an Intel Core i5 or i7. When it comes to graphics cards, some excellent choices are the 6 GB version of the GTX 1060 (avoid the 3 GB version), the 8 GB GTX 1070, and the 8 GB GTX 1080. AMD GPUs aren’t recommended due of their lack of CUDA support.

A brief stroll through the Nxt Marketplace

The Nxt Marketplace (click to expand).

A few days ago, I began accepting Nxt donations for this site. Nxt is a feature-rich cryptocurrency written in Java and built entirely from the ground up that relies on pure proof-of-stake to secure its blockchain. One of its most popular features is the Nxt Marketplace (formerly called the Digital Goods Store). Think of it as a decentralized, censorship-resistant eBay built on top of the blockchain.

There are a lot of listings on the Nxt Marketplace ranging from fairly mundane stuff like domain names and video game keys to things that would probably get you instantly banned from eBay. I spent the afternoon going through the various listings on offer and collected some of the more interesting ones for this post.

For example, here is a listing for a four-year-old laptop that cost $1,999 when new which can be yours for $3,600 (each NXT was worth $0.06 when the ad was posted):

Product: MAC BOOK PRO
Date: 10/29/2018 4:42:40
Price: 60,000 NXT
Seller: NXT-G8QA-W46K-DVFB-9N9LW (View Store)
Quantity: 1

Model A1398 mid2014
Perfect condition

Or what about a Bitcoin-themed oil painting painted by the seller himself which can be yours for 25 BTC or 500,000 NXT (worth about $9,000 at the time)? It didn’t sell and the comments on the BitcoinTalk thread are hilarious:

Product: Masterpiece Bitcoin Oil Painting
Date: 11/21/2014 17:35:04
Price: 500,000 NXT
Seller: NXT-BCFU-753H-BKF3-AJJ82 (View Store)
Quantity: 1

Masterpiece Bitcoin Oil Painting by The Divine Ruler His Majesty The King Cuong V Truong.

This masterpiece oil painting was painted using an ancient hand writing style known as "The Chinese Calligraphy"

Asking price is 25 BTC.
At the time this ad is posted on 11/20/2014. That's around 500,000 NXT coins.

Details at:
https://bitcointalk.org/index.php?topic=807265.0

Imaginary air guitar lessons (no delivery required, you just dream it):

Product: Imagenary Air guitar lessons
Date: 2/15/2015 2:23:56
Price: 6 NXT
Seller: NXT-N84U-FNHB-RSTT-BVF7S (View Store)
Quantity: 4

Just dream it

Love:

Product: Love
Date: 12/4/2014 12:32:36
Price: 2 NXT
Seller: NXT-3PAG-3ZSH-S4W7-CGBPU (View Store)
Quantity: 999,999,999

Buy love! I know money can't buy love but man atleast it's cheap lol why not spend 1 NXT to buy it?

Happiness:

Product: Happiness
Date: 12/4/2014 13:07:42
Price: 2 NXT
Seller: NXT-3PAG-3ZSH-S4W7-CGBPU (View Store)
Quantity: 999,999,999

Buy Happiness! I know that money can't buy happiness, but atleast try it, its cheap, what can you lose?

Nothing:

Product: Nothing
Date: 12/4/2014 13:07:42
Price: 2 NXT
Seller: NXT-3PAG-3ZSH-S4W7-CGBPU (View Store)
Quantity: 999,999,999

Yes, you read it correctly, it's nothing. You will get what you paid for, you will get Nothing!

Nothing but 50% off:

Product: Marketplace Buyer Experience
Date: 10/21/2014 6:24:28
Price: 1 NXT
Seller: NXT-9SDF-57KE-H8RU-9BHWY (View Store)
Quantity: 999,999,999

Buy the experience of having bought something on the Nxt marketplace for only 1 NXT.

A sip of beer (for the seller, not you):

Product: Sip of Beer
Date: 6/21/2020 21:57:33
Price: 5 NXT
Seller: NXT-ZY4T-YEXP-7PQC-GM6PB (View Store)
Quantity: 100

A sip of beer that I'll drink for your health tonight as a big thank you for your support ;)

Chicken nuggets:

Product: Chicken nuggets
Date: 8/29/2017 21:35:51
Price: 10 NXT
Seller: NXT-5JTH-SU4U-ZJJ3-9AC74 (View Store)
Quantity: 999,999,999

Chicken nuggets with real chicken inside !
Because we all love nuggets ...

An honest opinion on your looks:

Product: Want Me To Rate Your Looks (1-10)? Ask Me!
Date: 2/27/2015 6:48:40
Price: 10 NXT
Seller: NXT-3GNP-5JYB-3GNU-8AG7Y (View Store)
Quantity: 100

Title says it all, send a picture and I will give you my personal opinion!

The personal details of rich people:

Product: Contact Database of 2000 Family Offices
Date: 12/30/2017 11:48:52
Price: 2,500 NXT
Seller: NXT-Z8V9-LYM5-JZMG-A9JR2 (View Store)
Quantity: 1

This is a continuously updated contact database of high net worth families across the globe. There are 2,000 wealthy families in this database. The database, delivered in Excel format includes the investors' names, company names, emails, phone numbers, addresses, investment interests, and biographies.

A competing cryptocurrency project:

Product: Cryptocurrency TippingCoin
Date: 9/6/2018 21:28:36
Price: 3,000,000 NXT
Seller: NXT-RNNV-MPRH-ZULM-6TACV (View Store)
Quantity: 1

Cryptocurrency TippingCoin for sale, 999 Million Coins to buyer trasnfered direct to their Waves Wallet. 1 million are in circulation.
Sale includes all digital assets incuding website www.tippingcoin.org with lifetime hosting and instagram account @tippingcoin.
The TippingCoin Token was Built on the Waves Platform and listed On the Waves Dex Exchange.
The 999 million coins are valued at approx $20 million USD
All the above is listed at the heavily discounted price of just 1% of true value at $200,000 = 3 Million NXT

The seller’s favorite Christmas turkey recipe:

Product: Christmas turkey recipe
Date: 12/8/2014 4:22:18
Price: 4 NXT
Seller: NXT-U3C3-7Z5A-CT8C-E66EC (View Store)
Quantity: 30

This is my own favorite Christmas turkey recipe. I'll send you a dropbox link to claim your recipe

A very short story:

Product: Super Short Stories
Date: 10/18/2017 14:12:34
Price: 15 NXT
Seller: NXT-KK2H-VCUZ-HBLD-4T2VK (View Store)
Quantity: 1,000,000

Send me 15 NXT and recieve a Super Great, Super Short Story. Each uniquely handwritten, and very short.

And finally, whatever this is supposed to mean:

Product: The Feels Goodman Trust
Date: 9/9/2017 11:52:34
Price: 100 NXT
Seller: NXT-RL3B-B8XP-MQ98-EDXNJ (View Store)
Quantity: 1,000

The Feels Goodman Trust is a not-very-profitable non-charitable organization specializing in tackling existential dilema, usually with alcohol, drugs and hookers.

"What will I get from my contribution" I hear you ask?

You will get the satisfaction, the smug elitism even, of KNOWING you are better than everyone else, those plebian insects that don't care about anyone but themselves.

Why does Bill Gates do it? Because that shit feels good, man.

My thoughts on the Bitcoin ETFs

There’s a lot of talk right now in the Bitcoin community about the new Bitcoin ETFs. Some of the discussion has been negative in tone because let’s face it – the whole idea goes against the original value proposition of Bitcoin as “being your own bank” – i.e. a permissionless, decentralized, and censorship-resistant peer-to-peer currency that doesn’t rely on centralized institutions and trusted third parties.

That being said, I can also understand why some people might prefer to invest in a Bitcoin ETF instead of holding actual coins. Bitcoin ETFs do have a place even though they aren’t for someone like me. Older people for example who tend to know little about computers and technology but might be interested in this fancy new Bitcoin thing that everyone seems to be talking about could be well served by throwing some money into a Bitcoin ETF. Such people are likely to fall victim to hacks, scams, or otherwise accidentally lose their private keys if they attempted to buy and store bitcoins themselves so it can be safer to let other people who are (hopefully) more knowledgeable than them deal with the security issues involved – even if it comes with a 1.5% annual management fee in the case of BlackRock’s offering.

But if you have the technical skills and know-how to purchase bitcoins and safely store your own private keys then I would stay away from these ETFs. Bitcoin isn’t like gold where self-custody is a difficult and expensive ordeal. Bitcoins don’t require a pickup truck to haul or take up valuable space in your basement. You don’t need to worry about declaring your bitcoins to state authorities when crossing between national borders. As long as you can remember a 12-word passphrase, your coins will always be yours.

The Song dynasty in China was the first to issue paper money called jiaozi. These were valued at a certain exchange rate for gold, silver, or silk. Originally, the notes were meant be redeemed after three years, to be replaced by new notes for a 3% service charge. However, as more of them were printed without older notes being retired, inflation became rampant and all of the notes eventually became worthless. It’s stories like these that provide historical precedent as to why some people in the Bitcoin community dismiss these Bitcoin ETFs as “paper coins”.

In 1933, the US government enacted Executive Order 6102 which forbid its citizens from owning gold outside of small amounts of gold jewelry and coins. Bitcoin is unique among asset classes because it threatens the role of the US dollar as the global reserve currency. Could the state attempt to nationalize the bitcoin holdings of its citizens in a last-ditch attempt to save a collapsing dollar? If anti-cryptocurrency politicians like Elizabeth Warren manage to secure key positions of power then such a scenario could be more likely than you think.

In 1938, Nazi Germany enacted the Decree on the Registration of Jewish Property – a law that forced Jewish people to register their wealth with the government – paving the way for state-sanctioned theft on a massive scale. Those who were fortunate enough to leave Germany before the Holocaust were forced to relinquish up to 90% of their wealth. More recently, the government of Cyprus seized a portion of their citizens’ bank accounts in 2013 in order to make up for its own mismanagement of their economy. If the majority of people had their savings in Bitcoin and cryptocurrencies which they held their own private keys to, then these governments would have been powerless to confiscate their citizens’ wealth.

Coinbase is listed as the custodian for 8 out of 11 Bitcoin ETFs in the US including Grayscale’s and BlackRock’s offerings. Will Coinbase become the next Inputs.io? The next Mt. Gox? The next Cryptsy, QuadrigaCX, Celsius Network, and FTX? Wallets can be hacked and employees can go rogue. The only way to protect yourself from situations like these is to hold the private keys to your bitcoins. However, if you don’t trust yourself to safely store your own private keys and are only interested in speculating on the price of Bitcoin (rather than using it as a currency) then a Bitcoin ETF might be the best option for you. Just understand that you’re not holding actual bitcoins. “Not your keys, not your Bitcoin” is a often quoted phrase in the Bitcoin community and it’s specifically situations like these where it matters most.

Top 50 cryptocurrencies described in five words or less

In 2018, there was a popular infographic that made rounds on social media that listed the top 100 cryptocurrencies in terms of market cap with short descriptions of each project (click to expand):

The author also wrote lists for the top 200 and 300 cryptocurrencies:

I found these lists to be useful because they provided a bird’s-eye view of the cryptocurrency industry at the time. The lists are a bit outdated now because a lot of new projects have appeared since then while others have fallen out of popularity. As a bit of a homage to the original series, I decided to create an updated list for 2024. Due to time constraints, I have shortened the list to include only the top 50 cryptocurrencies:

Here is the same list as a table:

Market cap rankCoinTickerDescription
1BitcoinBTCFirst decentralized cryptocurrency.
2EthereumETHSmart contract platform.
3TetherUSDTStablecoin pegged to USD.
4BNBBNBBinance exchange utility token.
5SolanaSOLFast, cheap transactions and DApps.
6USDCUSDCStablecoin backed by USD.
7XRPXRPGlobal money transfer network.
8ToncoinTONTelegram-linked scalable blockchain.
9DogecoinDOGEFun, meme-inspired cryptocurrency.
10CardanoADADecentralized app platform.
11TRONTRXDecentralized app platform.
12AvalancheAVAXFast, scalable smart contracts.
13Shiba InuSHIBEthereum-based meme token.
14PolkadotDOTInteroperable multi-blockchain platform.
15ChainlinkLINKDecentralized oracle network.
16Bitcoin CashBCHPeer-to-peer electronic cash.
17UNUS SED LEOLEOBitfinex exchange utility token.
18DaiDAIStablecoin pegged to USD.
19NEAR ProtocolNEARFast, scalable smart contracts.
20PolygonMATICEthereum L2 scaling solution.
21UniswapUNIDecentralized Ethereum token exchange.
22LitecoinLTCSilver to Bitcoin’s gold.
23KaspaKASSecure, scalable PoW cryptocurrency.
24PepePEPEMeme-inspired cryptocurrency.
25Internet ComputerICPDecentralized world computer.
26Ethereum ClassicETCImmutable smart contracts.
27Artificial Superintelligence AllianceFETFetch.ai utility token.
28MoneroXMRPrivate, anonymous cryptocurrency.
29AptosAPTScalable smart contracts in Move.
30StellarXLMFast, cheap cross-border transfers.
31RenderRNDRDecentralized GPU rendering.
32HederaHBARAsset tokenization platform.
33CosmosATOMInteroperable blockchain ecosystem.
34ArbitrumARBEthereum L2 scaling solution.
35CronosCRODeFi and metaverse platform.
36FilecoinFILDecentralized storage network.
37OKBOKBOKX exchange utility token.
38MantleMNTEthereum L2 scaling solution.
39MakerMKRDai decentralized governance token.
40VeChainVETSupply chain transparency blockchain.
41StacksSTXBitcoin smart contracts and DApps.
42InjectiveINJInteroperable DeFi smart contracts.
43ImmutableIMXEthereum NFT L2 scaling solution.
44First Digital USDFDUSDStablecoin pegged to USD.
45SuiSUIFast smart contracts.
46OptimismOPEthereum L2 scaling solution.
47BittensorTAODecentralized machine learning models.
48BonkBONKDog-themed Solana memecoin.
49The GraphGRTDecentralized indexing system.
50NotcoinNOTTelegram-based play-to-earn token.

I hope this post is helpful to anyone interested in investing in cryptocurrencies. If you find a mistake then feel free to post it in the comments.

Riecoin: First impressions of Primecoin’s little brother

Riecoin is a math-focused cryptocurrency launched in 2014.

Those who have been active in the Bitcoin and cryptocurrency space for a while are probably aware of Primecoin (XPM) – a cryptocurrency that contributes to scientific and mathematical research by searching for primes. There has been a lot of discussion about how wasteful Bitcoin mining is in terms of energy usage and resources and Primecoin’s innovative proof-of-work algorithm is viewed by some in the cryptocurrency community as a potential way of turn mining into something that can be more useful for society. But Primecoin isn’t the only altcoin with mathematical research in mind out there – there’s Riecoin (RIC) too.

While Primecoin and Riecoin have their own independent development teams and communities, saying that Riecoin is Primecoin’s little brother seems like quite an accurate description. Both were developed by pseudonymous developers: Primecoin was launched in 2013 by Sunny King who would later go on to develop the first proof-of-stake coin in the form of Peercoin while Riecoin was launched in 2014 by a developer who went by the name of gatra on the BitcoinTalk forum. Perhaps as a nod to Satoshi Nakamoto, both Sunny King and gatra also stepped away from development of their coins after a few years and handed over the reins to their respective communities.

Both coins are CPU mineable (although Primecoin can be mined more efficiently with GPUs now) which is a bit of a rarity in today’s ASIC dominated world. While SHA-256-based coins like Bitcoin and Namecoin and scrypt-based coins like Litecoin and Dogecoin have been dominated by ASICs for a several years now, coins like Primecoin and Riecoin show that mining with regular home computers is still feasible in this day and age.

In terms of differences, Primecoin has 1 minute blocks, no maximum cap on coins, continuous difficulty adjustment, block rewards that are determined by the current difficulty, and a centralized checkpointing system. Riecoin on the other hand has 2.5 minute blocks, a maximum cap of 84 million coins, difficulty retargeting every 12 hours, and block rewards of 50 coins – halving every 4 years.

Both coins look for chains of prime numbers but Primecoin looks for Cunningham and bi-twin chains while Riecoin looks for chains of primes with minimum possible distances between each other. Primecoin also uses a combination of the Euler-Lagrange-Lifchitz and Fermat tests to prove primality (a faster but less accurate method) while Riecoin uses the Miller-Rabin test to test for primality (a slower but more accurate method).

Market cap-wise, Primecoin is certainly in the lead. As of July 8, 2024, Primecoin has a market cap of nearly $1.4 million while Riecoin’s is only $500,000. Both coins had fair launches with no signs of premines, instamines, ninjamines, and so on that plague the cryptocurrency community (I’m looking at you Bytecoin). From the Riecoin announcement thread:

“Fair launch:

Since this is a new PoW, it is very hard to define a starting difficulty that avoids instamining. To overcome this and contribute to a fair launch, the first 576 blocks will have no reward and the next 576 will linearly increase and reach the full reward at block 1,152, after 4 difficulty adjustments were performed. Besides avoiding instamining, this should allow time for those who want to compile their own clients. Expect the starting difficulty to be hard.

Source code will be provided a few days before launch, but the PoW functions will be replaced by stubs. The idea is that everyone would be able to examine the code and confirm that there’s nothing strange and it is indeed pretty similar to Bitcoin’s. Everyone would be able to compile it, see if they have the correct dependencies, etc. but it won’t run. At launch time, when the final code is released, everyone could easily check that the only thing that changed is the PoW code, so you’d only have to check the diff of a few lines of code and recompile.”

If you are interested in what Riecoin has to offer then I encourage you to visit the official website. It has all of the information you need to download, install, and run the software and guides to set up mining either by yourself or in a pool. There is also a handy link to download the entire blockchain bootstrap so that you don’t have to spend hours to days waiting for the client to sync up with the network.

Alternatively, if mining isn’t your cup of tea then you can head over to FreiExchange and buy them directly.

So far, I’ve been mining on a mid-range gaming laptop with an Intel Core i7-8750H for the last three hours and it takes little less than a day on average to mine a block. That being said, I don’t recommend mining on laptops for extended periods since their thermal designs aren’t as good as desktops.