I am going to be at #IIW next week. Would love to connect with you if you share common interests with me in serving humanity in a post AGI-world, or more generally for protocols, platforms and product related to identity, agentic commerce and related areas.
Send me a DM!
Not a great analogy. Earth doesn't have a choice in being the center of the solar system. Collaboration with lower intelligences is.
It may very well be a property of intelligences that there can be space for only one "Super Intelligence" in one Universe.
See the experience of lower intelligences on Earth, as a small scale experiment.
Terence Tao proposes what he calls a "Copernican view of intelligence".
Instead of buying into the common, one-dimensional narrative that artificial intelligence will simply evolve from "subhuman" to "superhuman" and ultimately make humanity entirely redundant, Tao urges us to look at the bigger picture.
Much like the Copernican revolution proved the Earth is not the center of the universe, Tao suggests we need to realize that human intelligence isn't the only, or necessarily the highest, form of intellect. Historically, we have treated other forms of storing or creating knowledge—like animals, books, and computers—as secondary. However, we actually exist within a much richer universe of intelligence.
Both human intelligence and computer intelligence possess their own distinct strengths and weaknesses. The true potential lies not in viewing them as direct competitors, but rather in focusing on collaboration. By working together, humans and computers can achieve additional things that neither could accomplish on their own, requiring us to think in much wider terms than just what humans or computers can do alone.
Having studied symmetry my whole adult life, I have come to the belief that we don’t fully know why symmetry is so important in physics. It may be more than one reason. Or it may be one reason. We aren’t there yet to be able
to call it.
We don’t even fully know what it is. We dont even know if symmetry and redundancy are different, equivalent or exactly the same thing. We dont know if Supersymmetry is a symmetry. We cant say easily what E8 is a symmetry of other than things made from E8.
If you were simply to change the definite article at the beginning of this post, it instantly becomes a great point. If you leave it, it remains a fascinating boast. Either way, it’s great food for thought. Thx.
We are entering an era where people could live longer and longer with improving health while also having fewer and fewer opportunities to afford those outcomes.
Agents will become the primary user interface for most people, replacing apps. That means Agents will mediate discovery of what to buy and the act of purchase itself. Often, it will need to do this autonomously with Human Not Present (HNP).
Autonomous agentic commerce will need three things to work. 🧵
The biggest question for crypto:
will AI use it?
Say an instance of ChatGPT, or Claude, wants more compute.
Does it pay by wire transfer, credit card, or crypto?
On the one hand, trad finance doesn't work well for AIs.
Like—how do they KYC? They have no passport, address, social security number, or even name.
Crypto works much better—it's already digital, it's permissionless, AIs can already query the blockchain, etc.
On the other hand, we might see an 'agent' model:
each AI is treated as an agent of some specific human, and that human does the KYC, is responsible for what the AI does, etc.
(Which brings up a related question: who is legally responsible for what an AI does?)
Either way, some work needs to be done to plug the world of AI into the world of trading and payments. Either that work will be natively digital and crypto-based, or it'll be reliant on a human 'master' for the AI.
Which direction it goes in has huge implications for the world.
One of those is the future of crypto.
2) Purchase Delegation
A protocol where the human specifies what the Agent can buy, for how much, from whom and until when. Sellers only honor purchases by agent if these conditions are met.
See AP2 (Google), ACP (OpenAI), TAP (Visa).
Couldn't the Agent simply pretend to be a user using the app and side-step all that?
I expect that operating systems will clamp down to only allow automation that uses such designated protocols.
Social networks will similarly require it to protect themselves against slop.
Yes. Ubiquitous access to agents will surely result in all traditionally human-generated content and interactions (articles, comments, videos) being overwhelmed with slop unless measures are taken.
What can be done about it? 🧵
Say a user wants their Agent to post on Twitter on their behalf. With XAA, Twitter will be able enforce that the Agent must show proof that the user approves this specific post through a step-up authentication that requires user presence.
Detecting whether content itself was generated using AI is going to be impossible very soon.
However, with these two elements in place we will have a workable system.
A human-only social network needs two basic things:
1) The social network should require human verification of every account. This tells others that a human runs the account and also which other accounts they run.
2) The social network should require that the human sign off on every post in a way that ensures the human is present when signing. Most common way is to require biometrics.