AI needs to serve people, science, and society

Henry Ford’s Faster Horse

The Great AI Fallacy

Embodiment Factors

Revolution

Coin Pusher

Royal Society Report

Public Research

Public Research

Public Research

Public Research

Mercutio

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.

Weather

Weather

\(p\)-Fairness and \(n\)-Fairness

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)]

A Question of Trust

NACA Langley

Data Science Africa is a bottom up initiative for capacity building in data science, machine learning and AI on the African continent

AI@Cam

• Developing the vision
  • Engaged over 100 members of the University community across 30 departments/institutes, start-ups, and large businesses.
  • Supported 6 new funding bids}

The Accelerate Programme

• Research
• Teaching and learning
  • Ramp or Bridge model
• Engagement

Data Trusts Initiative

Progress So Far

In its first 18 months of operation, the Initiative has:

• Convened over 200 leading data ethics researchers and practitioners;

• Funded 7 new research projects tackling knowledge gaps in data trust theory and practice;

• Supported 3 real-world data trust pilot projects establishing new data stewardship mechanisms.

Conclusions

• New Capabilities surprise society.
• But they are part of an ongoing revolution.
• Our approaches attempt to build interdisciplinary responses based on shared understanding of the real problems we face.