The Engineer in Society
“ ‘When someone seeks,’ said Siddhartha, ‘then it easily happens that his eyes see only the thing that he seeks, and he is able to find nothing, to take in nothing. […] Seeking means: having a goal. But finding means: being free, being open, having no goal.’ ”
Hermann Hesse
\[ \text{data} + \text{model} \stackrel{\text{compute}}{\rightarrow} \text{prediction}\]
\[\text{data} + \text{model} \stackrel{\text{compute}}{\rightarrow} \text{prediction}\]
Data Science Africa is a bottom up initiative for capacity building in data science, machine learning and AI on the African continent
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.
Later in the 1940’s, when I was doing my Ph.D. work, there was much talk of the brain as a computer and of the early digital computers that were just making the headlines as “electronic brains.” As an analogue computer man I felt strongly convinced that the brain, whatever it was, was not a digital computer. I didn’t think it was an analogue computer either in the conventional sense.
A human-analogue machine is a machine that has created a feature space that is analagous to the “feature space” our brain uses to reason.
The latest generation of LLMs are exhibiting this charateristic, giving them ability to converse.
But if correctly done, the machine can be appropriately “psychologically represented”
This might allow us to deal with the challenge of intellectual debt where we create machines we cannot explain.
LLMs are already being used for robot planning Huang et al. (2023)
Ambiguities are reduced when the machine has had large scale access to human cultural understanding.
book: The Atomic Human
twitter: @lawrennd
The Atomic Human pages cuneiform 337, 360, 390 , Royal Society; machine learning review and 25, 321, 395, MONIAC 232-233, 266, 343, MacKay, Donald, Behind the Eye 268-270, 316, psychological representation 326–329, 344–345, 353, 361, 367, human-analogue machine 343–5, 346–7, 358–9, 365–8, human-analogue machine (HAMs) 343-347, 359-359, 365-368.
podcast: The Talking Machines
Guardian article on How African can benefit from the data revolution
Guardian article on Data Science Africa
blog posts: