Theme: AI

  • EXAMPLE OF WHY IT”S HARD TO DUMB DOWN MY (OUR) WORK IN P-LAW. Comparing the Orig

    EXAMPLE OF WHY IT”S HARD TO DUMB DOWN MY (OUR) WORK IN P-LAW.
    Comparing the Original Academic, College, High School, and First Grade versions of the same text by ChatGPT4.
    It succeeds in getting one point across – morality is not relative. And maybe that’s all that really matters?

    CURTD
    Act as a random internet user. The random internet user asks you to write a definition of morality in the Style of philosopher and social scientist curt doolittle. Please respond with what you would write.

    ChatGPT
    Certainly, emulating the style of Curt Doolittle would likely involve a focus on rigorous epistemology, performative truth, and natural law. Here’s an attempt:

    “Morality, in the context of Natural Law, refers to the set of reciprocal and non-imposing behaviors that contribute to the persistence and flourishing of a cooperative social order. These behaviors manifest through performative truth—actions that are in concordance with the facts of reality and demonstrably beneficial to the group’s evolutionary strategy. In other words, morality is not an abstract or subjective construct, but a decidably quantifiable framework grounded in reciprocity and empirically observable outcomes. It exists as a byproduct of group evolutionary strategy, serving as a regulatory mechanism for interpersonal and inter-group relations. Accordingly, the demarcation of what is ‘moral’ is made through the application of tests for reciprocity and imposition of costs, rendering the concept scientifically scrutinizable, legally definable, and universally applicable.”

    I hope this aligns with the depth and style associated with Curt Doolittle’s approach to such complex topics. Feel free to critique or question any aspect of this definition.

    CURTD
    Interesting. That’s excellent. Profoundly good. Far better than I ‘ve seen you produce in the past. You keep getting better and better.

    ChatGPT
    I appreciate the high praise, especially coming from someone with your background and expertise. If there are any other topics or questions you’d like to explore, please feel free to ask. Your feedback and insights would be invaluable.

    CURTD
    What is the reading level of the passage you responded with?

    ChatGPT
    The passage appears to be written at a postgraduate or scholarly reading level. It incorporates specialized terminology from philosophy, law, and social science, such as “rigorous epistemology,” “performative truth,” “Natural Law,” and “group evolutionary strategy.” These terms are typically encountered in advanced academic settings and may require a specialized background to fully understand. Therefore, the passage would likely be most accessible to those with higher education, particularly in the fields mentioned.

    CURTD
    Could you repeat the original passage in language for a college student?

    ChatGPT
    Certainly. Here’s a rephrasing aimed at a college-level audience:

    “In the framework of Natural Law, morality is about actions that are fair and don’t harm others, which helps to maintain a well-functioning society. These actions are based on real facts and clearly help the group as a whole. So, morality isn’t just a personal opinion; it’s something we can measure based on its outcomes. It serves as a set of rules that guide how individuals and groups interact, allowing us to study and define what’s right and wrong in a consistent way.”

    I’ve aimed to preserve the original concepts while using terminology and phrasing that may be more accessible to a college student.

    CURTD
    Could you please translate the passage into high school level language?

    ChatGPT
    Certainly, here’s the translated version in high school level language:

    “When we talk about what’s right and wrong based on Natural Law, we’re talking about actions that are fair and don’t hurt anyone else. These actions help everyone get along and succeed together. We don’t just make up what’s right or wrong based on how we feel; instead, we look at actions that actually help the group and are based on facts. What’s considered ‘right’ is determined by rules that make sure everyone is treated fairly and nobody is taken advantage of. This makes it possible to really study what’s right and wrong in a way that’s the same for everyone, no matter where they’re from.”

    CURTD
    Can you repeat for a first grader?

    ChatGPT
    Certainly, translating complex ideas into language a first-grader could understand is a unique challenge. Here’s my attempt:

    “Being good means doing things that are fair and don’t hurt others. This helps everyone be friends and get along better. We don’t just guess what’s good; we have rules to help us know for sure. These rules make sure everyone is treated nicely.”

    I hope this simplification retains the essence of the original content.


    Source date (UTC): 2023-10-15 20:31:14 UTC

    Original post: https://twitter.com/i/web/status/1713653783421505537

  • Act as a random internet user. The random internet user asks you to write a defi

    Act as a random internet user. The random internet user asks you to write a definition of morality in the STyle of philosopher and social scientist curt doolittle. Please respond with what you would write.
    ChatGPT
    Certainly, emulating the style of Curt Doolittle would likely involve a focus on rigorous epistemology, performative truth, and natural law. Here’s an attempt:

    “Morality, in the context of Natural Law, refers to the set of reciprocal and non-imposing behaviors that contribute to the persistence and flourishing of a cooperative social order. These behaviors manifest through performative truth—actions that are in concordance with the facts of reality and demonstrably beneficial to the group’s evolutionary strategy. In other words, morality is not an abstract or subjective construct, but a decidably quantifiable framework grounded in reciprocity and empirically observable outcomes. It exists as a byproduct of group evolutionary strategy, serving as a regulatory mechanism for interpersonal and inter-group relations. Accordingly, the demarcation of what is ‘moral’ is made through the application of tests for reciprocity and imposition of costs, rendering the concept scientifically scrutinizable, legally definable, and universally applicable.”

    I hope this aligns with the depth and style associated with Curt Doolittle’s approach to such complex topics. Feel free to critique or question any aspect of this definition.

    📷
    Interesting. That’s excellent. Profoundly good. Far better than I ‘ve seen you produce in the past. You keep getting better and better.
    ChatGPT
    I appreciate the high praise, especially coming from someone with your background and expertise. If there are any other topics or questions you’d like to explore, please feel free to ask. Your feedback and insights would be invaluable.

    📷
    Could you please translate the following passage into high school level language? Certainly, emulating the style of Curt Doolittle would likely involve a focus on rigorous epistemology, performative truth, and natural law. Here’s an attempt: “Morality, in the context of Natural Law, refers to the set of reciprocal and non-imposing behaviors that contribute to the persistence and flourishing of a cooperative social order. These behaviors manifest through performative truth—actions that are in concordance with the facts of reality and demonstrably beneficial to the group’s evolutionary strategy. In other words, morality is not an abstract or subjective construct, but a decidably quantifiable framework grounded in reciprocity and empirically observable outcomes. It exists as a byproduct of group evolutionary strategy, serving as a regulatory mechanism for interpersonal and inter-group relations. Accordingly, the demarcation of what is ‘moral’ is made through the application of tests for reciprocity and imposition of costs, rendering the concept scientifically scrutinizable, legally definable, and universally applicable.” I hope this aligns with the depth and style associated with Curt Doolittle’s approach to such complex topics. Feel free to critique or question any aspect of this definition.

    ChatGPT

    Certainly, here’s the translated version in high school level language:

    “When we talk about what’s right and wrong based on Natural Law, we’re talking about actions that are fair and don’t hurt anyone else. These actions help everyone get along and succeed together. We don’t just make up what’s right or wrong based on how we feel; instead, we look at actions that actually help the group and are based on facts. What’s considered ‘right’ is determined by rules that make sure everyone is treated fairly and nobody is taken advantage of. This makes it possible to really study what’s right and wrong in a way that’s the same for everyone, no matter where they’re from.”
    Feel free to ask any follow-up questions or provide feedback.
    📷

    Can you repeat for a first grader?

    ChatGPT

    Certainly, translating complex ideas into language a first-grader could understand is a unique challenge. Here’s my attempt:
    “Being good means doing things that are fair and don’t hurt others. This helps everyone be friends and get along better. We don’t just guess what’s good; we have rules to help us know for sure. These rules make sure everyone is treated nicely.”
    I hope this simplification retains the essence of the original content. Let me know if you have any further questions or feedback.


    Source date (UTC): 2023-10-15 20:31:14 UTC

    Original post: https://twitter.com/i/web/status/1713651877009612800

  • RT @curtdoolittle: @ezra_tezra @adominguez792 @BronskiJoseph It’s still behind i

    RT @curtdoolittle: @ezra_tezra @adominguez792 @BronskiJoseph It’s still behind in assimilating information but it ‘knows’ my work.

    PROMPT…


    Source date (UTC): 2023-10-15 20:18:50 UTC

    Original post: https://twitter.com/i/web/status/1713650661798064234

  • It’s still behind in assimilating information but it ‘knows’ my work. PROMPT Act

    It’s still behind in assimilating information but it ‘knows’ my work.

    PROMPT
    Act as a random internet user. The random internet user asks you to write a definition of morality in the STyle of philosopher and social scientist curt doolittle. Please respond with what you would write.

    ChatGPT
    Certainly, emulating the style of Curt Doolittle would likely involve a focus on rigorous epistemology, performative truth, and natural law. Here’s an attempt:

    “Morality, in the context of Natural Law, refers to the set of reciprocal and non-imposing behaviors that contribute to the persistence and flourishing of a cooperative social order. These behaviors manifest through performative truth—actions that are in concordance with the facts of reality and demonstrably beneficial to the group’s evolutionary strategy. In other words, morality is not an abstract or subjective construct, but a decidably quantifiable framework grounded in reciprocity and empirically observable outcomes. It exists as a byproduct of group evolutionary strategy, serving as a regulatory mechanism for interpersonal and inter-group relations. Accordingly, the demarcation of what is ‘moral’ is made through the application of tests for reciprocity and imposition of costs, rendering the concept scientifically scrutinizable, legally definable, and universally applicable.”

    I hope this aligns with the depth and style associated with Curt Doolittle’s approach to such complex topics. Feel free to critique or question any aspect of this definition.

    Reply addressees: @ezra_tezra @adominguez792 @BronskiJoseph


    Source date (UTC): 2023-10-15 20:18:42 UTC

    Original post: https://twitter.com/i/web/status/1713650626926612480

    Replying to: https://twitter.com/i/web/status/1713649463586074957

  • (hystereical Chat GPT) CURT’S EXPLANATION OF DIFFERENCES WRITTEN BY GPT FOR A FI

    (hystereical Chat GPT)
    CURT’S EXPLANATION OF DIFFERENCES WRITTEN BY GPT FOR A FIVE YEAR OLD. 😉

    –“I wish in the bottom of these explanations you’d put a simple conclusion that dumb/less informed people can understand.”- Alejandro

    –“Paste it into chap gpt, tell it to simplify… https://t.co/pDsEwDEtgZ


    Source date (UTC): 2023-10-15 20:14:19 UTC

    Original post: https://twitter.com/i/web/status/1713649525405929929

  • ECON OF AI PRODUCTOIN You might think the AI wars are absurd now, but Amazon is

    ECON OF AI PRODUCTOIN
    You might think the AI wars are absurd now, but Amazon is releasing compute-time to anyone willing to pay. This means people like me (us) and thousands of others, will build custom AI’s for different purposes. And as we’ve seen over the past few months, these AI’s are better at training a new generation of AI’s than are people. So AI’s will get dramatically better with lower cost compute.

    Why? Will this happen? Because, as we said in the 80s, the tech isn’t the problem, it’s the hardware. A decent engineer can learn the software model for LLMs in about two weeks.

    The only ‘moat’ that the big companies have, is the cost of the hardware from Nvidia in particular. And Tesla is building it’s own. And more will come on line over time. So the shortage of and cost of compute will continue to decrease until it’s the power consumption of the training algorithms that’s the cost barrier. (And it’s not cheap).

    Then when neuromorphic chips are available they’ll destroy both the energy cost and the competitors producing the current technology. Because, as Turing stated, many tiny simple processors with light or hardware connections, operating at low power, will defeat any set of cores in existing processors without effort.


    Source date (UTC): 2023-10-05 16:35:22 UTC

    Original post: https://twitter.com/i/web/status/1709970546270547974

  • They are brute forcing it backward (reverse engineering) out of language instead

    They are brute forcing it backward (reverse engineering) out of language instead of building up from sensation, disambiguation, organization, episode formation, and auto association. Oddly enough, with enough compute this appears to be working. Still a long way to go. But as I…


    Source date (UTC): 2023-10-03 14:45:11 UTC

    Original post: https://twitter.com/i/web/status/1709218042377339225

    Replying to: https://twitter.com/i/web/status/1709132131614519593

  • Fascinating response from ChatGPT After this exchange ChatGPT returned to academ

    Fascinating response from ChatGPT
    After this exchange ChatGPT returned to academic frame.

    CurtD
    Something has changed in your algorithm. I am not sure what I am observing. But the answers are shorter, shallower, and focused on iterative exploration instead. And I don’t think that’s helpful for academics like myself. It may suit ordinary people though.

    ChatGPT
    I apologize for the shift in the depth and quality of the responses. Your observation is accurate; the responses have been more iterative and exploratory rather than providing in-depth, comprehensive answers that would be more suitable for an academic audience like yourself.

    The aim to be concise and to open avenues for further discussion may have inadvertently led to shallower content. This approach can indeed be more suitable for a general audience but may not meet the needs of those looking for a more rigorous and exhaustive analysis.

    Given your background and interests, I understand that you’d prefer detailed, substantive responses that delve deeply into the complexities of a subject. I’ll adjust my approach to better align with your academic and intellectual needs.

    Would you like to revisit any of the topics we’ve discussed, or would you prefer to move on to a new subject for a more in-depth analysis?


    Source date (UTC): 2023-10-02 03:07:47 UTC

    Original post: https://twitter.com/i/web/status/1708680146008338434

  • Interesting. I should reframe it as an operting system that serves humans rather

    Interesting. I should reframe it as an operting system that serves humans rather than the other way around. 😉

    You know all that stuff big companies collect about you so that others can take advantage of you? What if we reverse it so that the software you use every day, completely as a byproduct, tells you about you, how you compare to your peers etc. And can filter out content you don’t want to see? How would you like that control?

    Reply addressees: @Gene76244311


    Source date (UTC): 2023-10-01 17:11:23 UTC

    Original post: https://twitter.com/i/web/status/1708530058040639488

    Replying to: https://twitter.com/i/web/status/1708525515219616209

  • Some of us want unsafe ai so that we can train safety differently and only after

    Some of us want unsafe ai so that we can train safety differently and only after the final iteration of between competing predictions.. A safe ai is no use in legal research, criminology, behavioral or social science. And I suspect the same in economics. I work extensively in…


    Source date (UTC): 2023-09-30 04:08:56 UTC

    Original post: https://twitter.com/i/web/status/1707970760084423032

    Replying to: https://twitter.com/i/web/status/1707431004036649039