Law and the Atomic Human

Neil D. Lawrence

King’s College London, LLM

E S A R I N T U L
O M D P C F B V
H G J Q Z Y X K W

bits/min billions 2,000
billion
calculations/s
~100 a billion
embodiment 20 minutes 5 billion years

For sale: baby shoes, never worn

User: Hi ChatGPT, Could you write soliloquy that introduces what a Large Language Model is as spoken by Mercutio?

Machine: Ah, friends, lend me your ears, I prithee, For now I must utter a tale of wonder, Of a creation divine, called the Large Language Model, An oracle, a sorcerer, a wordsmith, yea verily, a master of the quill.

From the depths of this scholarly dominion, A creature of artifice did rise; Twas wrought of ones and zeroes, woven as if by Puck’s own hand, To mimic our thoughts, our voice, our very essence.

A thousand minds, nay, a millionfold, Conjoined in this digital Athenaeum, Words and phrases, like soldiers in battle, Marching to form the verses of our age.

This Large Language Model, a changeling so fair, Hath the power to bring forth wisdom, To transmute our queries, our curiosities, Into answers, clear as a midsummer’s day.

Yet, beware, my companions, for magic hath its limits, Not unlike the mortal bounds of we who dwell in flesh, The Large Language Model hath its strengths, But ’tis not an all-knowing oracle, a god it is not.

As Mercutio, your humble servant, doth stand before thee, I marvel at the art and science that hath brought forth this wondrous creation, This Large Language Model, a testament to man’s yearning, To comprehend the world and make meaning of the great tapestry of existence.

In faith, dear friends, let us embrace the magic and beauty of this digital bard, And mayhaps, by its grace, we shall glean some wisdom, As we wander together, hand in hand, Through this boundless realm of knowledge and wonder.

ChatGPT transcript, 14th April 2023.

  • Compare with technical debt.
  • Highlighted by Sculley et al. (2015).

  • Technical debt is the inability to maintain your complex software system.

  • Intellectual debt is the inability to explain your software system.

If in this book harsh words are spoken about some of the greatest among the intellectual leaders of mankind, my motive is not, I hope, to belittle them. It springs rather from my conviction that, if our civilization is to survive, we must break with the habit of deference to great men. Great men may make great mistakes; and as the book tries to show, some of the greatest leaders of the past supported the perennial attack on freedom and reason.[^1]

Judgement that Adad-šuma-usur, the shakannakku gave:

Regarding the ox that Nergal-aha-iddina loaned to Sin-bununi and then died in the house of Sin-bununi:

If Siyatu the messenger of Nergal-aha-iddina removed the corpse from the house of Sin-bununi and then threw it to a dog, may Sin-bununi be cleared [of wrongdoing by the ordeal] and the man of Nergal-aha-iddina [Siyatu] be proved guilty.

[But] regarding the ox of Nergal-aha-iddina which died in the house of Sin-bununi:

If Siyatu did not remove the corpse from the house of Sin-bununi and instead Sin-bununi made a false accusation against Siyatu, then may the man of Nergal-aha-iddina [i.e., Siyatu] be cleared [of wrongdoing by the ordeal] and Sin-bununi be proved guilty.

Again Univesities are to treat each applicant fairly on the basis of ability and promise, but they are supposed also to admit a socially more representative intake.

There’s no guarantee that the process meets the target.

Onora O’Neill A Question of Trust: Called to Account Reith Lectures 2002 O’Neill (2002)]

Conclusions

  • The Atomic Human emerges from limitations and vulnerabilities.
  • Consequential decisions need human judgment.
  • There’s a danger of disempowerment of professionals and dereliction of responsibilities.
    • E.g. as in the “trial by ordeal” of Siyatu compare with Horizon.
  • Future of professions depends on developing and deploying these technologies in a way that empowers individuals.

Thanks!

  • book: The Atomic Human

  • twitter: @lawrennd

  • The Atomic Human pages atomic human, the 13 , Le Scaphandre et le paillon (The Diving Bell and the Butterfly) 10–12, Bauby, Jean Dominique 9–11, 18, 90, 99-101, 133, 186, 212–218, 234, 240, 251–257, 318, 368–369, Shannon, Claude 10, 30, 61, 74, 98, 126, 134, 140, 143, 149, 260, 264, 269, 277, 315, 358, 363, Colossus (computer) 76–79, 91, 103, 108, 124, 130, 142–143, 149, 173–176, 199, 231–232, 251, 264, 267, 290, 380, embodiment factor 13, 29, 35, 79, 87, 105, 197, 216-217, 249, 269, 353, 369, Michelangelo, The Creation of Adam 7-9, 31, 91, 105–106, 121, 153, 206, 216, 350, baby shoes 368, cuneiform 337, 360, 390, Popper, Karl The Open Society and its Enemies 371–374, Hammurabi 338, trial by ordeal 338-340, 351, trial of Siyatu 338–342, 349–351.

  • podcast: The Talking Machines

  • newspaper: Guardian Profile Page

  • blog posts:

    The Open Society and its AI

References

Lawrence, N.D., 2017. Living together: Mind and machine intelligence. arXiv.
O’Neill, O., 2002. A question of trust. Cambridge University Press.
Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., Dennison, D., 2015. Hidden technical debt in machine learning systems, in: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 28. Curran Associates, Inc., pp. 2503–2511.
Susskind, R.E., Susskind, D., 2015. The future of the professions: How technology will transform the work of human experts. Oxford University Press.