Mind the Gap: Bridging Innovation’s Supply and Demand in the AI Era

Philosopher’s Stone

The Attention Economy

Herbert Simon on Information

What information consumes is rather obvious: it consumes the attention of its recipients. Hence a wealth of information creates a poverty of attention …

Simon (1971)

Revolution

The Future of Professions

Human Capital Index

• World Bank Human Capital Index
• UK outperforms USA and China
• Measures health and education

Productivity Flywheel

Inflation of Human Capital

• Strength in Human Capital double edged sword.
• Automation creates efficiency.
• But skills risk becoming redundant.

Inflation Proof Human Capital

• Does automation totally displace the human?
• Or is there an irreducible core?

Uncertainty Principle

• Machines rely on measurable outputs
  • Quantified aspects of humans easier to automate
  • Essential aspects of humanity are the hardest to measure
• Implies: atomic human is difficult to quantify

Homo Atomicus

• Not in A-level results
• Not in hospital waiting lists
• In the quality of human interaction

New Productivity Paradox

• Current productivity flywheel relies on measurement

Coin Pusher

Innovation Economy Challenges

• Over emphasis on “macro economic supply interventions”
• Under emphasis on maping “micro economic demand” to “micro economic supply”

Digital Failure Examples

The Horizon Scandal

The Lorenzo Scandal

Commonalities

• Policy-reality disconnect
• Poor local needs understanding
• Missing feedback loops

Implementation Issues

• Inflexible top-down approach
• Limited stakeholder input
• Inadequate technical oversight

Key Lessons - Engagement

• Engage stakeholders at all levels
• Design flexible systems
• Build feedback mechanisms

Key Lessons - Implementation

• Use phased rollouts
• Ensure technical competence
• Set realistic timelines

What do People Want?

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

“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)

AI in Healthcare: Public Perspectives

“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

• Support for reducing teacher workload.
• Concerns about screen time and support for human interaction.

AI in Education: Public Perspectives

“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

AI in Education: Public Perspectives

“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

Dialogue Summary

• Enhance, don’t replace humans
• Strong governance first
• Fair distribution of benefits
• Keep human-centered services

Dialogue Summary

“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)

What’s the solution?

Supply Chain of Ideas

• Ideas flow from creation to application like physical supply chains
• Parallels with traditional economic supply chain management
• Particularly relevant for IT and AI solutions

Supply Chain of Ideas

• Current imbalance between supply and demand sides
• Current focus on creating new technologies/companies
• Under-focus on real-world needs

Supply Chain of Ideas

• Need to map idea demand to supply
• Focus on understanding current “stock” of ideas
• Active management of idea resources
• Shaping supply to meet demand

AI cannot replace atomic human

New Attention Flywheel

Example: Data Science Africa

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

Example: Cambridge Approach

ai@cam

How ai@cam is Addressing Innovation Challenges

• A-Ideas (across 20 departments)
• Policy lab (with Bennett, Minderoo)
• HPC Pioneer projects (with RCS, C2D3)
• Accelerate programme (Schmidt Sciences funded)