Allison Clift-Jennings, co-founder and CEO of Filament, spoke with our team about the work her company is doing to scale the Internet of Things through connectivity and contractuality. She also explains why she believes blockchain technology is one of the most important contributions to computer science in the last 50 years.
By Via Science Marketing
Tell us about yourself.
My name is Allison Clift-Jennings, and though I’m currently helping to drive Filament towards this interesting world of autonomous machines, I’m an engineer at heart. I received a computer science degree and have worked within startups for the last 20 years. There’s something beautiful about the merging of new technology and entrepreneurism that I find really appealing and I can’t seem to stay away from it.
Outside of my professional life, I’m enamored with complex systems theory and like to explore it in the areas of permaculture and music composition.
Filament works to connect industrial infrastructure across secure, wireless networks building a sort of industrial Internet of Things. Can you tell us more about the Telehash, TMesh, Blockname, and Blocklet technologies Filament uses in its operations?
Filament is fundamentally a company whose core competencies involve protocol development and deployment. Most successful companies usually have some core strength that sets them apart, and ours is that our company and the people in it think very seriously and intently about how protocols can help the world operate in a more cooperative, balancing way.
Inside this area of focus, Filament has identified two components of the Internet of Things that needed significant effort to be able to scale and decentralize alongside the massive number of devices expected in the next decade. The first involves private, secure, peer-to-peer network communications — what we call connectivity. The second involves bringing economic capabilities to devices, allowing them to establish and enforce contractual agreements between themselves, other machines, and with people — we call this contractuality.
Telehash (and TMesh, its IoT device implementation)
Telehash is the protocol stack we’ve developed that focuses on the connectivity aspect. In short, it’s a peer-to-peer network protocol that allows devices to establish secure end-to-end channels between themselves and the endpoints they communicate with. Most network devices today claim to be secure, but only provide a secure link to their hub, which is often an internet-connected computing appliance. This appliance is often less secure and may use insecure network channels up to the cloud.
Telehash, in contrast, establishes the full encryption channel all the way to the cloud server it is sending its data to. This is what we mean when we say “end-to-end”. It’s been really difficult to do this in the past, because devices are not very powerful and often run off of batteries. A complete protocol was needed to allow these devices to transmit data packets across network transports such as LPWAN, Bluetooth LE, LTE/Cellular, as well as IP-based networks as used on the Internet. Telehash is a next-generation protocol inspired heavily by Jabber/XMPP* —a very popular instant messaging protocol.
Jeremie Miller, our chief scientist, is the founder of Jabber and invented XMPP and has used his experience with Jabber (currently at the height of its popularity with over 1B daily users) to inform how best to build this new network protocol for devices.
Blocklet (and its subsets Blockname, Penny Bank, and others)
Blocklet is the protocol stack we’re developing that focuses on the contractuality aspect. It’s a bit more difficult to describe Blocklet, as we don’t have many things that exist today to compare it to. In essence, this is a protocol stack that allows physical devices — the things in the Internet of Things — to extend their capabilities beyond compute and connectivity, and move into having economic capability.
Filament has a very strong ethos that claims there is raw economic value at the boundary between the physical and the digital. Specifically, the very threshold where a device can use sensors to sense physical phenomena in the real world (such as temperature, geolocation, or vibration) is where the vast majority of the value of the Internet of Things lies. Similarly, devices that use actuators to control physical systems (such as valves, switches, or control boards) also contain this vast value. Think of this capability as the reflex system of the Internet, just like the reflex system in your body or perhaps, digital skin for the Internet.
This is somewhat incongruent with the current mindset in the Internet of Things industry today that claims the majority of the value lies in the cloud. And to that position’s defense, recent developments in machine learning — specifically the recurrent and convolutional neural network developments within deep learning — has demonstrated significant value in the cloud. However, without getting valid data into the cloud, and more importantly I believe, without having the ability to effect change out into the physical world by actuation, the full potential of AI/ML in the cloud will not be realized.
To add some background on why we consider this an economic issue, consider some concepts from Economics 101. If we think about the core concepts of economics and markets, it fundamentally comes down to trust. If you buy a loaf of bread from a store, you are trusting the store to provide the bread they claim they have. You are trusting that the price of the bread won’t fluctuate significantly from one day to another. You’re also trusting that the store will accept your type of money to pay for the bread. Also, the store is trusting that you are giving them authentic, non-counterfeit money. And they’re trusting they will be able to use that money to pay for operating costs of their organization. Trust is everywhere in market economics, and to the degree that trust is unavailable, degraded, or misrepresented, a similar level of friction and inefficiency will exist.
So, in the context of Blocklet, trust is the atomic unit. If we can physically guarantee some basic levels of trust at a device level, we can then build higher-order economic capabilities on top, such as establishing value, creating markets, and even providing for devices to transact directly with each other — literally devices buying and selling goods and services between each other at machine speed. We establish this physical guarantee by using a secure element on all of our devices. This is an integrated circuit chip that gives us strong capabilities of cryptographic key storage and computation and lets us mathematically prove things like device identity (can I guarantee who I say I am?), and secure device communication (can I guarantee that what I send you hasn’t been tampered with?)
Without these protocol primitives that can ensure trust and secure communication, we believe the Internet of Things will be unable to realize its full potential.
What do industry leaders need to know about integrating this technology into their daily operations?
Contrary to the detail in which our platform was described in the previous section, it’s incredibly easy to deploy our technology in an industrial operations environment. Filament did the hard work upfront in order to make it easy to use.
A good way to describe a typical deployment is with an example. Consider a power distribution utility company. They often own and manage hundreds of thousands of power poles that provide power to their customers in urban, suburban, and rural environments. These poles are core infrastructure that have limited lifespans and they often fail from age or extreme events like heavy storms. A company could deploy our product by purchasing monitoring for their poles by simply attaching our devices to their poles. The devices are completely self-contained, including the tilt sensors, the battery, the network, and the secure element — and both the Telehash and Blocklet capabilities already embedded in it. They can deploy 1, 10, or 100,000 at once if they wish. All devices communicate with each other once configured with the proper permissions. We have other devices that can connect this large ad-hoc network to the cloud, if desired.
How did you first start researching and working with these technologies?
I’ve personally been interested in distributed systems for many years, though my professional career led me to other areas outside of this discipline. However, back around 2004, I began getting really interested in the very early work of cryptocurrencies. This was prior to Bitcoin, Ethereum, and the like. There was work being done by David Chaum with eCash, Nick Szabo with his Contracts with Bearer, and Ryan Fugger with his original Ripple protocol. For me, these were the earliest revelations that there is something amazing here if some of the core problems could be solved. One of the largest issues was this contrast between the need to trust a system, and desiring decentralization of that system, so it wouldn’t be abused later. This dilemma led to now-famous concepts like the Byzantine General’s Problem.
Our CEO Colin Gounden believes blockchain has the potential to change the landscape in the same way the Internet did. Do you agree with this estimation? How might it impact energy and heavy industry?
To continue the thought from the last section, there was a time during the mid 2000s where some interesting work was happening within distributed systems and cryptoeconomics, but it still contained fundamental problems that needed solutions. Then, there was a paper released in 2009 that described this new cryptocurrency idea called Bitcoin, and used a data structure called a Blockchain that could solve the dilemma of balancing trust with decentralization. At the time it was too early to tell if it would actually work, but in hindsight this was, in my opinion, one of the most important contributions to computer science in the last 50 years. I believe it’s up there in importance alongside spread-spectrum radio technology and the invention of the transistor. So I fully agree with Colin on this position: it’s hard to overstate how important blockchain is as it’s solved a major issue within this space. It’s interesting to consider other fields of research that are also possibly having their “blockchain” moment — most notably in the field of genetics with the invention of CRISPR/Cas9 technology.
A Harvard Business Review article published earlier this year argued that in order for a disruptive blockchain revolution “many barriers — technological, governance, organizational, and even societal — will have to fall.” What barriers to widespread adoption of blockchain have you encountered?
This is a difficult position for me to agree with. Yes, it does cause one to consider that if this technology can solve such a fundamental problem of establishing trust between parties, without authority, that it will by extension disrupt nearly all existing systems of balance and harmony that use authority. However, the Internet did just this thing 20 years ago, when it allowed people to communicate with multiple, rich modes of media, with each other, in a very decentralized way. And the television before that. And the telephone before that. And the telegraph before that. Each of those inventions did disrupt some industries — but often those industries were best positioned to take advantage of the new capabilities, though not all did.
The biggest barrier to blockchain adoption we’ve seen is simply a lack of understanding of why it’s important. Not so much how it works — because you don’t need to know how it works to gain benefit from it any more than you need to know how a telephone, or telegraph, or radio waves, or an internet router works in order to gain benefit from it. But most barriers we come across today are that people often don’t realize what blockchain-based technology can do for them. They don’t understand what problem it solves. It’s not quite as obvious at first pass as, say, a smartphone is. It’s easy to describe “computer and phone in your purse”. It’s a little harder to describe “a new form of governance and trust without coercion in your purse”. But it’s no less revolutionary.
What do you think is the next big thing to come from blockchain and IoT?
Blockchain-enabled devices is big enough!
In all seriousness, I believe we have a lot of progress to be made in getting these small devices at the edge to be much more smart — embedding machine learning capabilities directly into them, rather than running massive cloud-based data centers. While I believe there will always be a place for the cloud, it’s disproportionately distributed on the cloud side, and a movement to edge-based compute and learning could give the industry lots of new capabilities we thought were unavailable to us today.