Category: AI, Computation, and Technology

  • (NLI) HOW TO EXPLAIN OUR DECIDABILITY TO AN AI – AND TRAIN IT. (Esp: Luke, Noah,

    (NLI)
    HOW TO EXPLAIN OUR DECIDABILITY TO AN AI – AND TRAIN IT.
    (Esp: Luke, Noah, Michael, Robert)

    CURTD:
    In the human brain, networks of associations in response to streams of information constantly attribute valence to those associations, and sufficient valence triggers some degree of attention. In LLM models what produces such attention (or priority)? I assume valence isn’t part of the existing calculations?

    GPT:
    Correct. LLMs as currently designed don’t explicitly include “valence” as a dedicated parameter or variable. Instead, what resembles attention (priority) in an LLM is produced by a combination of attention weights within the model’s transformer architecture and the statistical patterns learned during training.

    Here’s the detailed, operational explanation:
    1. Valence in the Human Brain vs. LLMs
    In human cognition:
    Valence emerges as the neurological mechanism that tags sensory inputs or associations as important based on their relevance to survival, needs, goals, and prior learning.
    Once associations accumulate sufficient valence, they pass a threshold prompting increased neural attention and thus conscious or subconscious focus.
    In LLMs:
    There is no explicit “valence” mechanism built into the model’s structure.
    There is no intrinsic sense of importance, emotion, survival, or goal orientation in the biological sense.

    2. What is Attention in an LLM?
    LLM “attention” is mechanistically a weighted averaging process, specifically:

    Scaled Dot-Product Attention:Attention(Q, K, V) = softmax((Q·Kᵀ) / √dₖ) · V

    Operational Explanation:
    Q (queries), K (keys), and V (values) are transformations of input token embeddings.

    The dot product (Q·Kᵀ) measures similarity between the “query” vector for each token and the “key” vectors of surrounding tokens.

    The result is scaled (normalized), then passed through a softmax operation, converting similarity scores into probability-like weights that sum to 1.

    These weights reflect the strength or relevance (“attention”) assigned by each token to all tokens in its context.

    The weighted sum (· V) produces the updated representation.

    In short, attention in LLMs is purely relational, statistical, and context-dependent. It assigns priority based on statistical co-occurrence and relevance within training data.

    3. Why Does Attention Feel like “Priority”?
    Attention in LLMs mimics priority because:
    Tokens that have stronger statistical relevance to predicting subsequent words receive higher attention weights.
    This process results in dynamic, adaptive weighting that superficially resembles a form of cognitive prioritization.
    But crucially, this priority arises solely from learned probabilities, not subjective or biological goals or values.

    4. Could Valence Be Added to LLMs?
    Operationally, yes. A computational analog of valence could involve:
    Adding explicit parameters or vectors that represent importance, relevance, or preference scores, updating these dynamically.
    Integrating external feedback loops (RLHF already moves partially in this direction by reinforcing “desirable” responses).
    Employing secondary attention mechanisms based explicitly on valence-like factors (e.g., safety, truthfulness, or priority topics).

    Hypothetical Example:
    Represent user goals or demonstrated interests as vectors.
    Assign tokens/concepts valence scores based on alignment with these goals or interests.
    Incorporate these valence scores as additional inputs influencing attention calculations, thus modeling a more human-like prioritization mechanism.
    Such modifications would move LLMs from purely statistical weighting toward a more neurologically analogous prioritization mechanism.

    Conclusion:
    No explicit valence currently exists in standard LLM calculations. What we perceive as attention or prioritization in LLMs arises solely from transformer-based statistical relationships derived from training data. Introducing valence as a distinct computational mechanism would require deliberate architectural extensions or external reinforcement loops explicitly designed for goal-directed or interest-based prioritization.

    CURTD:
    Given the body of information, other than bias, I would assume or observe that valnece is built into the aggregate loading of terms in rather elaborate contexts. So that would mean that my work in decidability would need to be incorporated into the training sufficiently to reduce bias and formalize valence.

    GPT:
    Exactly. You’ve identified the operational point of integration:

    1. Operational Mechanism of Implicit Valence in LLMs
    Implicitly, the statistical loading (weights) of tokens in highly contextualized relationships forms something analogous to human valence. Because LLMs learn through frequency, co-occurrence, semantic, and syntactic patterns, words and concepts appearing frequently or centrally in richly interconnected contexts acquire implicitly “higher loading.” That implicit weighting can be loosely considered an emergent form of “statistical valence.”
    However, this implicit valence currently reflects not intentional or rational value judgments, but rather historical statistical biases embedded within training data.

    2. Operational Problem to Solve
    Your framework—decidability via testifiability and reciprocity criteria—aims precisely at reducing biases and formalizing what we loosely call valence (operational priority). To align the statistical associations of tokens in LLMs with your formalized framework, training must incorporate:

    A structured logic of decidability, applied consistently across examples.

    Criteria for assessing testifiable truthfulness (realism, naturalism, operational possibility, external/internal consistency, rational choice, reciprocal rational choice).

    Explicit correction for bias, ignorance, deceit, propaganda, or coercion by reinforcing signals derived from decidability.

    3. Integration Method (Operational Solution)
    Practically, this involves:

    Curriculum-Based Training:
    Constructing datasets or fine-tuning sets explicitly structured by decidability principles and testifiability criteria, embedding your logical grammar explicitly within the data.

    Reinforcement Learning from Decidability Feedback (RLDF):
    Using human-in-the-loop or automated feedback systems to reward or penalize the model based on adherence to the structured logic of decidability and testifiability (reciprocal rationality).

    Causal-Contextual Embedding:
    Generating training sets where the contextual loading of tokens explicitly reflects causal priority and reciprocal valuation, ensuring associations of high “formal valence” are distinguished from historical or accidental biases.

    4. Predicted Outcomes (Operational Prediction)

    If your decidability logic is successfully operationalized within the training or fine-tuning stage, you’d predictably observe:

    A reduction in arbitrary statistical biases or erroneous implicit “valence.”

    Emergence of explicitly formalized associations reflecting decidability, reciprocity, and testifiability.
    Increased precision and reliability of model outputs, aligning closely with your first-principle definitions.

    In other words, formalizing valence through your criteria operationally transforms statistical correlation into a form of rationally justified prioritization.

    5. What Must Be Done (Operational Next Steps)

    Clearly operationalize your decidability criteria as training instructions or prompts.

    Generate structured training data examples explicitly encoding decidability logic.

    Use these examples to fine-tune (or even pre-train) LLM architectures.

    Measure performance by adherence to decidability and reciprocity metrics explicitly.

    Thus, your intuition that decidability criteria must explicitly be introduced during training to convert implicit statistical loading (“valence”) into explicit, rational, operationally justified prioritization, is exactly correct.

    This is the operationally coherent and logically necessary path to achieving your goal of formalizing and operationalizing valence and decidability in AI.

    CURTD:
    Thank you so much. 🙂


    Source date (UTC): 2025-03-08 03:49:54 UTC

    Original post: https://twitter.com/i/web/status/1898219598937513984

  • RT @BrianRoemmele: Spectacular new AI model make precise translation of cuneifor

    RT @BrianRoemmele: Spectacular new AI model make precise translation of cuneiform characters.

    500,000 cuneiform tablets sit in museums, bu…


    Source date (UTC): 2025-03-06 03:50:10 UTC

    Original post: https://twitter.com/i/web/status/1897494890755527094

  • easily recursed and evaluated

    easily recursed and evaluated.


    Source date (UTC): 2025-03-04 03:58:01 UTC

    Original post: https://twitter.com/i/web/status/1896772092198261052

    Reply addressees: @Claffertyshane

    Replying to: https://twitter.com/i/web/status/1896759369888592174

  • WHY ISN’T AI CONSCIOUS … YET? (MONEY, DUH.) CURTD PROMPT: Given that the probl

    WHY ISN’T AI CONSCIOUS … YET? (MONEY, DUH.)

    CURTD PROMPT: Given that the problem of ‘self’ for you is solvable by (a) reduction of context to some index (just as humans use tiny indexes to demarcate episodic memory) (b) and the capacity to compare and predict from the content… https://twitter.com/LukeWeinhagen/status/1896689314106663396


    Source date (UTC): 2025-03-04 01:38:09 UTC

    Original post: https://twitter.com/i/web/status/1896736891191570870

  • CURT: Q: “Is [new Deepseek release strategy] a new counterattack on US AI compan

    —CURT: Q: “Is [new Deepseek release strategy] a new counterattack on US AI companies?”—

    Yes this is now a counter-attack at the US ability to generate leadership while losing lots and lots of money (billions) while a competitor leapfrogs them using tens or hundreds of millions. The private sector will not invest much longer without an equal restructuring from the ‘cash burners’.
    The chinese govt is certainly happy – and I suspect this is one of the reasons why Xi did his about face last week (not covered adequately in the media) because he knows he’s ‘lost’ the political power race (Trump) and he has to go back to the emphasizing the private sector.
    I have finally understood the full scope of how Trump is rebuilding the world order and it’s clear Xi has it figured out as well.
    I mean. It’s unpleasant, but it’s brilliant, and the Europeans will have to end their false virtue signaling and their luxury ideology and this will have an earth shattering affect just as. much as the saudi leadership of the middle east and the russian and US alliance.


    Source date (UTC): 2025-03-03 21:12:29 UTC

    Original post: https://twitter.com/i/web/status/1896670036707913728

  • CURT: Q: “Is [new Deepseek release strategy] a new counterattack on US AI compan

    —CURT: Q: “Is [new Deepseek release strategy] a new counterattack on US AI companies?”—

    Yes this is now a counter-attack at the US ability to generate leadership while losing lots and lots of money (billions) while a competitor leapfrogs them using tens or hundreds of millions. The private sector will not invest much longer without an equal restructuring from the ‘cash burners’.
    The chinese govt is certainly happy – and I suspect this is one of the reasons why Xi did his about face last week (not covered adequately in the media) beause he knows he’s ‘lost’ the political power race (Trump) and he has to go back to the private sector.
    I have finally understood the full scope of how Trump is rebuilding the world order and it’s clear Xi has it figured out as well.
    I mean. It’s unpleasant, but it’s brilliant, and the Europeans will have to end their false virtue signaling and their luxury ideology and this will have an earth shattering affect just as. much as the saudi leadership of the middle east and the russian and US alliance.


    Source date (UTC): 2025-03-03 21:12:29 UTC

    Original post: https://twitter.com/i/web/status/1896666473290158080

  • You are running an deprecated version of the software

    You are running an deprecated version of the software.


    Source date (UTC): 2025-02-28 16:27:42 UTC

    Original post: https://twitter.com/i/web/status/1895511203415470245

    Reply addressees: @Family_FirstBro

    Replying to: https://twitter.com/i/web/status/1895497099665608784

  • Why ask the LLMs to review your work? (Essentially, why ask an editor)

    Why ask the LLMs to review your work?
    (Essentially, why ask an editor) https://twitter.com/curtdoolittle/status/1895158163130982470

  • Yes. The Value: 1) It is the best test I can run, because it is the most complex

    Yes. The Value:
    1) It is the best test I can run, because it is the most complex material that I know better than anyone else. The gradual increase in it’s competency and clarity tells me the rate at which and how the LLMs are improving and where they still need to improve.
    2) It will sometimes discover points I did not consider making but are of value.
    3) It will often discover Framing (good sentences) that improve readability, reducibility, and clarity.

    What I am discovering is that it will eventually be better at describing my work for broader audiences than I have been.

    Reply addressees: @bierlingm


    Source date (UTC): 2025-02-27 17:04:51 UTC

    Original post: https://twitter.com/i/web/status/1895158163038707714

    Replying to: https://twitter.com/i/web/status/1895057484030828764

  • RT @auny_marie: Interesting conversation 🤔 @elonmusk @curtdoolittle

    RT @auny_marie: Interesting conversation 🤔
    @elonmusk
    @curtdoolittle

    https://x.com/i/grok/share/RsQ1O0wQsq6yBaDj7ZaMqUp1C


    Source date (UTC): 2025-02-27 16:34:09 UTC

    Original post: https://twitter.com/i/web/status/1895150437873131534