Data First Culture

Henry Ford’s Faster Horse

Panacea

Introduction

Exercise: Score Yourself

• I am a data science:

1. follower (no visibility/influence)
2. some visibilty/influence
3. visibility and some influence
4. leader (lead on data and AI developments)

Information and Embodiment

Claude Shannon

Embodiment Factors

New Flow of Information

Evolved Relationship

Evolved Relationship

Intellectual Debt

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.

Public Dialogue on AI in Public Services

• September 2024 convened public dialogues.
• Perspectives on AI in priority policy agendas.

“I think a lot of the ideas need to be about AI being like a co-pilot to someone. I think it has to be that. So not taking the human away.”

Public Participant, Liverpool pg 15 ai@cam and Hopkins Van Mil (2024)

AI in Healthcare: Public Perspectives

Key aspirations include:

• Reducing administrative burden on clinicians
• Supporting early diagnosis and prevention
• Improving research and drug development
• Better management of complex conditions

AI in Healthcare: Public Perspectives

Illustrative quotes show the nuanced views:

“My wife [an NHS nurse] says that the paperwork side takes longer than the actual care.”

Public Participant, Liverpool pg 9 ai@cam and Hopkins Van Mil (2024)

“I wouldn’t just want to rely on the technology for something big like that, because obviously it’s a lifechanging situation.”

Public Participant, Cambridge pg 10 ai@cam and Hopkins Van Mil (2024)

AI in Education: Public Perspectives

Key quotes illustrate these views:

“Education isn’t just about learning, it’s about preparing children for life, and you don’t do all of that in front of a screen.”

Public Participant, Cambridge ai@cam and Hopkins Van Mil (2024) pg 18

“Kids with ADHD or autism might prefer to interact with an iPad than they would a person, it could lighten the load for them.”

Public Participant, Liverpool ai@cam and Hopkins Van Mil (2024) pg 17

AI in Crime and Policing: Public Perspectives

• Complex attitudes towards AI use.

Key quotes reflect these concerns:

“Trust in the police has been undermined by failures in vetting and appalling misconduct of some officers. I think AI can help this, because the fact is that we, as a society, we know how to compile information.”

Public Participant, Liverpool pg 14 ai@cam and Hopkins Van Mil (2024)

“I’m brown skinned and my mouth will move a bit more or I’m constantly fiddling with my foot… I’ve got ADHD. If facial recognition would see my brown skin, and then I’m moving differently to other people, will they see me as a terrorist?”

Public Participant, Liverpool pg 15 ai@cam and Hopkins Van Mil (2024)

AI in Energy and Net Zero: Public Perspectives

Representative quotes include:

“Everybody being able to generate on their roofs or in their gardens, selling energy from your car back to the grid, power being thrown different ways at different times. You’ve got to be resilient and independent.”

Public Participant, Cambridge pg 20 ai@cam and Hopkins Van Mil (2024)

“Is the infrastructure not a more important aspect than putting in AI systems? Government for years now has known that we need that infrastructure, but it’s always been someone else’s problem, the next government to sort out.”

Public Participant, Liverpool pg 21 ai@cam and Hopkins Van Mil (2024)

Summary

• AI should enhance rather than replace human capabilities
• Strong governance frameworks need to be in place before deployment
• Public engagement and transparency are essential
• Benefits must be distributed fairly across society
• Human-centered service delivery must be maintained

“We need to look at the causes, we need to do some more thinking and not just start using AI to plaster over them [societal issues].”

Public Participant, Cambridge pg 13 ai@cam and Hopkins Van Mil (2024)

A Question of Trust

A Question of Trust

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)]

The Great AI Fallacy

Digital Failure Examples

The Horizon Scandal

The Lorenzo Scandal

Commonalities

Gap between policy (macro) and on ground reality (micro) * Insufficient consideration of local needs and systems. * Lack of effective feedback mechanisms from micro to macro. * Rigid top-down implementation. * Insufficient engagement with end users and stake-holders

Complexity in Action

Data Selective Attention Bias

BMI Steps Data

BMI Steps Data Analysis

A Hypothesis as a Liability

“ ‘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

The Scientific Process

Number Theatre

Data Theatre

Sir David Spiegelhalter

The Art of Statistics

The Art of Uncertainty

Blake’s Newton

The MONIAC

Human Analogue Machine

HAM

Conclusion