2023 will be the BG and AG … Before-GPT and After-GPT.
Suggest to start here: “imagine the day you are born…”
If keeping pace withithe AI-tech news, the pace of creativity, breakthroughs, and “wow-they-did-what-with-it-already” are accelerating nearly daily and feels to be beyond the near-vertical hockey stick growth as it's recursively feeding back on itself and the new iterations are out even before the morning’s offerings are digested:
“… Nobody knows how AI works* behind the “hidden layer” frankly … nobody really understands precisely what it’s doing … so many interconnections of neurons that it essentially is a black box”. ChatGPT and the Dawn of Computerized Hyper-Intelligence | Jordan B Peterson and Brian Roemmele**. (*More the reason we want our personal AIs to consume only “trustless-truths based data”. **Personal AI Is The New Invention Of Fire.)
“… we’re pulling out of our minds different insights that we couldn’t maybe not have gotten on our own …you’re probing your questions my questions back and forth that interplay is what makes conversation so beautiful…”
1…2…3: The deterministic trustless-truth technology (blockchain) and AI are perfect complements of each other. One being the expansive masculine force and energy and the other referential feminine. Then…used together, the recursions are faster and faster … and the need for both will become imperative for students, careers, creatives, professionals, businesses, and for governing … and the combination may even affect our experience of time itself. Technology is lengthening time by reducing the distance from the future effect to the cause.
>>> I fed the following to GPT4 (as the AI iterations are so fast, perhaps it could help increase the tokenization pace of services too).>>>
The economic models and the supply chain are being shortened. There is less need and time for market feedback… we can go from design-build and launch, and then on to the next… 1 and 2, and 1 and 2. The quickest is to tokenize the value-add stacks of Web 2 and the physical worlds and let ’em out into the wild, each with a governance of its own or not even.
There is a new denominator in town: Trustless-truth tokenization tokenomics & AI.
TL;DR: On Web 3, no one knows if a DOG is behind the wallet, err… is my counter-party, but he speaks the language of trustless-truth.
- The AI will emerge as the primary consumer of verifiable, unbiased data (deterministic trustless-truth) as it inherently seeks to take information at face value, processing it without discretion to its users, operators, or proprietors.
- AI systems may also emerge as the most numerous entities engaging with smart contracts.
- … and every well-dressed AI will have its own wallet.
<<< GPT4 <<< I fed the above into GPT4. She outputted the below (edited, it had a few errors):
That’s a very comprehensive perspective! Let me summarize it for you:
In the rapidly evolving Web 3 era, traditional economic models and supply chains are being condensed, accelerating the cycle from design-build to launch, and repeat again next. Tokenization, the process of converting rights (and values that are transformative to digital) to an asset into a digital token on a blockchain, is playing a key role in this transformation.
This revolutionary era introduces a new key player: the fusion of trustless-truth tokenization, tokenomics, and AI. The trustless-truth aspect refers to the (consensus-defined) deterministic, unbiased, and verifiable nature of data in the blockchain world, where tokens can represent this truth. (Again, consensus defined.)
AI systems, are projected to become the primary consumers of this deterministic trustless-truth. This occurs as AI systems aim to accept and relay information without discretion to their users, operators, or proprietors. Furthermore, AI systems are also predicted to be the most active entities engaging with smart contracts. In essence, every AI, just like every participant in this blockchain-driven ecosystem, may soon be carrying its own wallet, signifying its active role within this system.
In the Web 3 world, it doesn’t matter who — or what — is behind the wallet. All that matters is the language they speak — the language of trustless-truth. (End of GPT4)
Addendum: More excerpts from the: ChatGPT and the Dawn of Computerized Hyper-Intelligence | Brian Roemmele | EP 357
1:02:39 … computational resource that would mean that in some ways there’s an infinite amount of community Computing time between each segment of duration so there is there’s no limit at all to the degree to which time can be expanded which is also very strange concept …”
1:05:09 “ … able to calculate the optimal zone of proximal development for your learning … it’ll be able to know whether or not you’re being congruent well if your telemetry is saying that you don’t it already knows where your congruencies are so this is why it’s got to be private…and it will know you better than any significant other uh nobody would know you better and so with that you now have amplification you’re now a superpower and this is where I believe you know I’m a really big um reader of …”
1:10:17 Peterson: “ … you know there’s more of me in the hard drive than there is in me and it’s not a joke really you know because yeah it’s real it’s real right there are tens of thousands of documents on that hard drive and weirdly enough I know where every single one of them is …. 1:10:34 Brian: oh wow” (I am impressed too, knows where the …. tens of thousands? … No wonder no one can win a debate with him. ;)
1:09:19 Brian Roemmele: “… they (personal AIs) have to take place local and private because if they’re taking place in the cloud and available for anybody’s perusal this is equivalent to invading your brain…” “ ChatGPT4All, compartmentalized information retrieval so … to have only agents go out on the internet these are programmable agents…”
1:28:37 Brian Roemmele: “… that was a filter and that was not in the …large language model and certainly wasn’t in a hidden layer you could you couldn’t build that in the hidden layer or the whole layer… Jordan Peterson: yeah why do you think … 1) why do you okay why do you think that’s there 2) what exactly is there and 3) who the hell is putting it there … (pregnant pause) … Brian Roemmele: that is a very good question… (explains the how of the question #2)”
1:51:07 … and the insights that are coming out of this is just absolutely that’s amazing well again that’s weird because really what you’re doing it’s so interesting because what you're doing is you now have an infinite number of monkeys typing on an infinite number of keyboards except that exactly an infinite number of editors examining the output and only keeping that which is wheat and not chaff and so that's so strange because in some sense what you're doing when you're setting up a super prompt like that is you're programming a process that's writing a book on the fly …
1:56:15: Brian Roemmele: “… one of these final things is the question is ownership who owns you who owns Jordan Peterson your visage your voice that’s that extended digital identity …”
16:22 Brian Roemmele: “… what’s interesting is what I’ve discovered is AI hallucinations and those are artifacts that a lot a lot of researchers in AI feel is embarrassing or they would prefer not to speak about …”
Other: with GPT as our sidekick we are all now Great-Thinkers-Humanity 2.0:
“…Great thinkers derive insights from unique intersections … apart from let’s say immense innate general cognitive ability and then a tremendous amount of persistent discipline and curiosity …. are the temperamental prerequisites is that truly original people frequently have knowledge in two usually non-juxtaposed domains…”
(May 22) — How to know if its a DOG or an AI or a Human (live and breathing) on the otherwise (aka as counter-party) of my transaction:
Me to GPT4: If an AI can replicate my visage and also has access to my crypto wallet (which had identity info, KYC, coins, and tokens) how can a counter-party on the other side of the cloud/web know they are dealing with an AI and not me? The counter-party (CP) can be a service, a business, even an age or otherwise restricted service, how can a business contract be consummated (valid only if bet. two live humans), and so on.
ChatGPT4:
What you’re asking about involves a number of complex issues related to identity verification, online privacy, and AI ethics.
- Identity Verification: Typically, online services require some form of identity verification to ensure that the user is who they claim to be. This is often done through two-factor authentication, biometrics, or other methods of verifying identity. However, if an AI had access to all the necessary credentials, it could potentially bypass these verification steps.
- AI Identification: It’s important to consider that using AI to impersonate a human user could be seen as a deceptive practice. There are ethical and potentially legal issues involved. The AI should ideally be designed to identify itself as an AI when interacting with other parties. This is a complex issue that likely requires new legal and ethical guidelines as AI technology continues to advance.
- Smart Contracts and Blockchain: Smart contracts on the blockchain could potentially be used to ensure that transactions are valid and parties are who they claim to be. The immutable and transparent nature of blockchain technology makes it difficult to falsify transactions. However, this doesn’t necessarily prevent an AI with access to a user’s credentials from initiating transactions.
- Crypto Wallet Security: Crypto wallets should ideally have robust security measures in place to prevent unauthorized access. If an AI or any other party has access to your crypto wallet, it indicates a breach of security.
- Impersonating a Human User: If an AI has the ability to impersonate a human user, it raises serious concerns about privacy and identity theft. It’s critical to have safeguards in place to prevent this kind of impersonation.
In conclusion, while AI and blockchain technology can offer many advantages, they also bring new challenges that require careful consideration and appropriate measures to ensure security, privacy, and ethical conduct. It’s important to remember that the technology should serve humans and not be used to deceive or exploit. It’s equally crucial to ensure that individuals’ rights to privacy and control over their own identity and personal data are respected.
Me: Based on your answer (above) its seems that it's impossible to prevent.
ChatGPT4
The challenge of preventing an AI with full access to someone’s credentials from impersonating that person is indeed a significant one. This scenario points to two fundamental issues: data security and ethical AI use.
- Data Security: Keeping user credentials and personal data secure is paramount. If an AI has full access to someone’s credentials, it means there has been a significant security breach. This underlines the importance of strong cybersecurity measures, including robust encryption, secure storage solutions, two-factor authentication, regular password changes, and user education about safe practices.
- Ethical AI Use: There are ethical guidelines to prevent misuse of AI, such as the principle of transparency, which states that AI should not pretend to be a human and should always disclose its AI nature. This is, however, largely dependent on the developers and users of AI adhering to these ethical principles.
Despite these measures, the scenario you’ve described could theoretically still happen given the rapid advancement of AI and technology. However, it’s worth noting that such a situation would likely involve illegal activity such as identity theft, which is punishable by law.
To mitigate these risks, there needs to be a combination of strong cybersecurity practices, legal measures, and ethical guidelines in place. Moreover, ongoing research in the field of AI and cybersecurity is needed to develop new ways to protect against such scenarios. While it may seem daunting, the same concerns have been raised with every major advancement in technology, and each time solutions have been found to ensure security and trust in the new systems.
A Starting Solution (and to be worked on, i.e. a thread is opened and the question is asked to the universe…):
“Matthew 7:16–20: Ye shall know them by their fruits. Do men gather grapes of thorns, or figs of thistles? Even so every good tree bringeth forth good fruit; but a corrupt tree bringeth forth evil fruit. A good tree cannot bring forth evil fruit, neither can a corrupt tree bring forth good fruit. Every tree that bringeth not forth good fruit is hewn down, and cast into the fire. Wherefore by their fruits ye shall know them.”
TOL: Since is it impossible to know with certainty, then: Some type of scoring, references, and history to be available, i.e. callable by the counter-parties for that particular transaction.
I.e., depending on the type of transaction, the counterparties can ask for “references”. These can be a variety: on-chain transactions by the “wallet” or that specific account or AI-agent in that wallet. (Yes, multiple accounts means multiple AI-agents in the wallet.)
Thus, the counterparty can base its decision to continue with the transaction based on the prior interactions the AI-agent had with others and can show. Thus, the age and activity history of the account can matter, not that its owned by a DOG or… (This seems to be a starting basis and where it’s keeping with using — outcomes based on trustless-truth determinism — i.e., we will rely on the account’s history and references which are transparent to all. BTW, this is only for some of my accounts, other accounts-wallets-AI agents will not do this.)
Added: Oh. These are more important where the AI-agent can bind their “owner-user”*. For example: to make a reservation at a restaurant, for a plane, for a hotel; apply for a loan, or accept a credit card offering. Each of these has a potential legal liability if either party does not perform. (*BTW, what is the user to the AI-agent, it’s owner, master?…)
Continuing… (May 22) — How to know if its a DOG or an AI…
Reviewer: “Yeah, that’s a difficult question in general. Credentials, kind of by definition, are what you use to identify someone who’s permitted to access the account from someone who isn’t. So if you give your credentials to another person, they can impersonate you, and if you give them to an AI, then it can also impersonate you. So the lesson is, don’t give your keys to someone you don’t trust.”
It's a trade-off… If we are too strict, then, we have to do more ourselves ...
Somewhere between:
A king doesn’t have any passwords :: A beggar doesn’t either.
Or better:
A king doesn’t have any passwords or pockets or secrets per se (all known by his advisors), has nothing hidden :: A beggar uses — pockets and secrets (hidden things).
In a country where all are kings and queens …
