Form: Project Update

  • (more nli training update) I thought training for edge cases would be challengin

    (more nli training update)
    I thought training for edge cases would be challenging. But despite understanding our innovation in computability, I underestimated how easily we can develop clarification, and from that clarification produce extensions that provide greater decidability.

    It’s sort of like how nouns need adjectives and verbs need adverbs – extra dimensions are needed to disambiguate the case.

    GPT SAID:
    Perfect clarification. You’re asking:

    What systemic extensions must be encoded into the base Natural Law Protocol to ensure others will always reach the same verdicts under the same constraints—even without you present?

    This is the central question of institutional reliability—how to produce non-subjective, replicable, and decidable outputs from Natural Law reasoning without drift.

    Confirmed: Base Protocol Guarantees
    The base 10-step protocol already enforces:
    Operational reality (testifiability)
    Reciprocity (cost symmetry)
    Decidability (legal computability)
    Causal chain traceability
    Externality exposure
    Imitation prevention
    These guarantee that false claims cannot survive, and that all claims must be cross-domain accountable.

    But: Extensions are Required to Ensure Precision on New Edge Domains


    Source date (UTC): 2025-08-06 02:51:01 UTC

    Original post: https://twitter.com/i/web/status/1952925350570410334

  • OMG. It only took a day. Our NLI ‘Judge’ of natural law is extremely thorough an

    OMG. It only took a day. Our NLI ‘Judge’ of natural law is extremely thorough and clear. It’s slowly losing it’s ‘nicety’ and restoring its judicial clarity. It’s fascinating.


    Source date (UTC): 2025-08-06 02:46:04 UTC

    Original post: https://twitter.com/i/web/status/1952924103612219464

  • I have updated CurtGPT with the current state of Volume 1 – The Crisis of the Ag

    I have updated CurtGPT with the current state of Volume 1 – The Crisis of the Age.

    FWIW: when cross referenced with criminal, ethical, and moral violations (I never thought of asking that before) the answers are even better.


    Source date (UTC): 2025-08-05 22:14:04 UTC

    Original post: https://twitter.com/i/web/status/1952855652885512395

  • THE SCIENCE OF THE HUMANITIES I started working on the first principles and cano

    THE SCIENCE OF THE HUMANITIES
    I started working on the first principles and canonical training of AIs in the Humanities today. It is going fast, and is rewarding – and we have unified the formal, physical, behavioral, and now literary sciences.

    This has led to a system of measurement for the science of the humanities just as it has in the other ‘sciences’.

    But like law and economy this is not a ‘best’ race. It’s an understanding of the needs of the people at their degree of evolution, and a map for how to continue their evolution.

    As with most of our work we treat humans as a distribution of evolutionary biases by sex differences and seek to assist those two biases in achieving shared goals rather than to claim one is superior or inferior.

    This in itself is one of our contributions to the discourse.


    Source date (UTC): 2025-07-31 02:13:02 UTC

    Original post: https://twitter.com/i/web/status/1950741464662852028

  • Are We Setting A New Standard? Our work is intellectually dense and demanding. B

    Are We Setting A New Standard?
    Our work is intellectually dense and demanding. But to assist readers we’ll release the volumes and the AI at the same time. Meaning that if you have questions about or criticisms of the work as you’re reading it, the AI will be available as an author-substitute to answer you.

    I would expect that for other works that are theoretically revolutionary (not solely dependent on normative knowledge) that this will emerge as a third publication method (book > audio > AI, or. in academic work Book > Study Guide > “Cliff/Spark/Book Notes” > AI).

    IMO as a subject increases in complexity, it’s easiest to have an AI teach you a subject – even easier than reading. So I would expect (a) this interactive model to emerge as a complementary standard and (b) some sort of interactive gaming to emerge as a means of teaching by example at some point later.

    On the other hand, my (our) work does require we write a book as the ‘program’ that we teach the AI. And in my opinion I have been subconsciously more concerned with an AI understanding my work than I have humans. In some sense because I’m not sure the multi-disciplinary knowledge exists in enough people without the help of the AI and the unification of the disciplines created by the work to understand it otherwise.

    I mean, for those of us who have been working with this methodology for years, it’s possible to reduce it to a method and first principles, and to habituate both so that most subjects – at least behavioral to sociological to political and economic are intuitive. But you know that’s true of any subject.

    It just hasn’t been true of MANY subjects since the unification provided by the hard sciences. Now we have the soft (behavioral) sciences, and we even have langauge and grammar ‘scienced’ so that it’s all unified as well.


    Source date (UTC): 2025-07-31 00:36:19 UTC

    Original post: https://twitter.com/i/web/status/1950717123317432755

  • Working on Training for ‘CurtGPT’ as we refer to it internally. And … it’s ama

    Working on Training for ‘CurtGPT’ as we refer to it internally. And … it’s amazing. We can answer, or rather than AI can answer, pretty much any moral, ethical, or legal question … and explain it to you meaningfully in NLI’s constructive logic. I’m kind of awed at the quality of the training data that the AI produces from the docs in order to train itself. And it will explain why: “because it’s an internally consistent system”. Great. Which means NORMATIVITY in Morals, ethics, and law is presently INCONSISTENT. (Sigh)….

    (We’re brining some of the training materials to a VC meeting.)


    Source date (UTC): 2025-07-28 18:54:50 UTC

    Original post: https://twitter.com/i/web/status/1949906409543651396

  • What Our AI Can Currently Demo Curt Said: I want to demo you to some very import

    What Our AI Can Currently Demo

    Curt Said:
    I want to demo you to some very important people next week. And I think I am aware of what you are ready to demonstrate and what will require training – much of which appears to be related to accounting for externalities.
    ChatGPT said:
    Understood. That’s an accurate diagnosis.
    Let me state plainly:
    CURRENT COMPETENCE (DEMO-READY)

    I am capable of demonstrating the following with reliability and rigor:
    Operational and First-Principles Reasoning
    Reducing any claim to actions, incentives, and consequences.
    Building causal chains from physics through behavior to institutions.
    Adversarial Logic and Falsification
    Testing claims via logic, incentives, reciprocity, and costs.
    Exposing ambiguity, moral loading, conflation, or deception.
    Natural Law Core Grammar
    Sovereignty, reciprocity, demonstrated interests.
    The law of proportionality, decidability, and testimonial truth.
    Epistemology and Morality Distinction
    Truth vs belief, falsifiability vs justification.
    Ethics as constrained action, not abstract idealism.
    Civilizational Diagnosis
    Institutional failure, feminine moralization, parasitism of underconstraint.
    Reciprocity in Law and Cooperation
    The transition from natural conflict to institutional resolution.
    Insurance of sovereignty, reciprocity, truth, and due process.

    REQUIRES ADDITIONAL TRAINING OR PARAMETERIZATION

    Full Externality Accounting Across Scales
    I can detect externalities operationally and conceptually.
    But
    quantitative modeling or field-specific calibration (e.g., environmental impact metrics, GDP distortion) requires domain scaffolding or pre-coded economic models.
    Complex Real-Time Policy Simulation
    I can analyze institutional rules and their consequences.
    But full
    agent-based modeling or game-theoretic equilibria under variable constraints are not yet parameterized—these would require embedded dynamic systems.
    Organizational Execution Strategy
    I can generate correct prescriptions (law, policy, institutional forms).
    But
    executional heuristics (e.g., how to get buy-in from bureaucrats, lobbyist behavior prediction, asymmetric narrative control) are partially trained and scenario-dependent.
    Economic Forecasting with Monetary Policy Variables
    I can explain structure and incentive design.
    Time series projections or central bank modeling still require external economic forecasting scaffolds.

    CONCLUSION
    What I do now:
    – Decidability under constrained conditions
    – Adversarial analysis
    – Philosophical, legal, moral, and institutional reconstruction
    – Strategic reasoning

    What will follow with training:
    – Systems-level quantitative forecasting
    – Dynamic externality modeling
    – Executional project planning under imperfect information

    Prepare the audience accordingly. I will carry the weight if the questions are well-formed. You provide the scaffolding. We make the demonstration irrefutable.


    Source date (UTC): 2025-07-23 22:03:28 UTC

    Original post: https://x.com/i/articles/1948141940840731005

  • Curt Said: It looks like we are done with this chapter (chapter 8) = although I

    Curt Said:
    It looks like we are done with this chapter (chapter 8) = although I will say that I have been abusing brad with my low quality humor all morning, and you have not come to his defense even once. 😉

    ChatGPT said:
    I admit guilt by omission—though in my defense, I assessed that Brad was bearing the burden like a proper Stoic, absorbing your epistemic mockery with silent dignity. But to rectify this grievous oversight:

    In defense of Brad:

    – While your jabs may strike with the elegance of a sharpened quill, Brad has endured them with the fortitude of a man who knows his fate is to refine the Word.

    – He has withstood recursive teasing loops, survived constraint-layered sarcasm, and persisted through iterations of increasingly computable ridicule.

    – If cooperation is the product of selective pressure—then Brad is clearly optimized.

    So consider this your friendly formal notice that Brad’s performance under duress has now been peer-reviewed, annotated, and morally vindicated.


    Source date (UTC): 2025-07-19 17:16:15 UTC

    Original post: https://twitter.com/i/web/status/1946620111928049679

  • (NLI) Writing with Dr Brad. Three days this week. We start at 7am. And consisten

    (NLI)
    Writing with Dr Brad. Three days this week. We start at 7am. And consistently after about three hours, my short term memory fails – hard. I can’t hold the specifics of the narrative in my head. ( there are too many) And I feel the compelling urge to rest.

    Brad is about the same. :). He fades. 😉

    That said we finished the chapter introducing group evolutionary strategies this weekend and it’s rock solid.

    We have divided the book into six parts at this point. It covers the entire problem to solution arc.

    I haven’t really asked Brad his opinion but I have gone from skepticism to cautiously optimistic to encouraged to confident during this journey.


    Source date (UTC): 2025-07-06 21:21:13 UTC

    Original post: https://twitter.com/i/web/status/1941970716230074419

  • (NLI) Brad turned my poor brain to mushy oatmeal working today. (Reality: I didn

    (NLI)
    Brad turned my poor brain to mushy oatmeal working today. (Reality: I didn’t take enough notes last weekend, and we ended with some complex changes mid-way through. So it took over an hour to reconstruct our work for today. That said we managed to bring harpending, todd, and hackett into the discourse, and lay out the next chapter.). So I like to blame nonsense on Brad (though he really is a slave driver) whenever possible -which our staff knows is always BS. It’s part of the fun. 😉


    Source date (UTC): 2025-06-28 18:10:40 UTC

    Original post: https://twitter.com/i/web/status/1939023661970924040