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

Henry Ford’s Faster Horse

Panacea

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.

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

NACA Langley

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

Innovation Economy Challenges

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

Supply Chain of Ideas

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

Bridging

ai@cam

Hygieia

ai@cam

Progress so far:

• 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
  • Five A-Ideas interdisciplinary projects
  • Policy Lab
  • 46 Pioneer computing projects

How ai@cam is Addressing Innovation Challenges

1. Bridging Macro and Micro Levels

A-Ideas Initiative - Challenge: Aligning high-level AI research with real-world needs. - ai@cam’s Approach: - Fund interdisciplinary projects addressing specific societal challenges. - Brought together 19 Departments across 6 Schools, ensuring diverse perspectives. - Examples: Projects on climate change, mental health, and language equity directly connect macro-level AI capabilities to micro-level societal needs.

Policy Lab

• Challenge: Translating academic insights into actionable policy.
• ai@cam’s Approach:
  • Connect researchers with policymakers and the public.
  • Produce policy briefs and engages in public dialogues.
  • Example: Collaboration with Bennett Institute and Minderoo Centre on AI governance policy brief.

2. Addressing Data, Compute, and Capability Gaps

Data: Data Intermediaries and maturity assessments

• Challenge: Improving liquidity of data access without compromising security.
• ai@cam’s Approach:
  • Data intermediaries for representing interests of those from whom data originates.
  • Assessment of data quality and data maturity assessments.

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.

2. Addressing data, Comptue and Capability Gaps

Compute: HPC Pioneer Project

• Challenge: Ensuring researchers have access to necessary compute resources.
• ai@cam’s Approach:
  • Provide access to the Dawn supercomputer for 46 projects across 20 departments.
  • Bridge the gap between advanced compute capabilities and diverse research needs.

2. Capability gaps contd …

Capability: Accelerate Programme for Scientific Discovery

• Challenge: Building AI skills across disciplines.
• ai@cam’s Approach:
  • Offer a range of AI training programs, from basic to advanced.
  • Equip domain experts with AI skills, bridging the capability gap.
  • Encourage peer to peer learning and sharing of materials supporting “AI Clubs”

The Accelerate Programme

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

3. Stakeholder Engagement and Feedback Mechanisms

Hopes and Fears Labs

• Challenge: Incorporating public perspectives in AI development.
• ai@cam’s Approach:
  • Collaborate with Kavli Centre for Ethics, Science, and the Public.
  • Conduct public dialogues on AI, ensuring diverse voices are heard.
  • Data intermediaries as an approach to capturing public voices

Cross-University Workshops

• Challenge: Ensuring AI initiatives align with diverse academic needs.
• ai@cam’s Approach:
  • Convene workshops on AI teaching and learning.
  • Engage Professional Services Staff to support capability building.

4. Flexible and Adaptable Approaches

AI-deas Challenge Development

• Challenge: Avoiding rigid, top-down research agendas.
• ai@cam’s Approach:
  • Use a bottom-up approach, allowing researchers to propose challenge areas.
  • Facilitate collaborative refinement of ideas through workshops.

5. Phased Implementation and Realistic Planning

Overall Strategy

• Challenge: Balancing ambition with realistic implementation.
• ai@cam’s Approach:
  • Adopt a phased approach, starting with pilot initiatives like AI-deas and Policy Lab.
  • Plan for gradual scaling based on lessons learned.

6. Independent Oversight and Diverse Perspectives

Steering Group

• Challenge: Ensuring balanced guidance and oversight.
• ai@cam’s Approach:
  • Workign with a cross-institutional Steering Group.
  • Include diverse expertise from different academic disciplines and professional services.
  • Close interactions with other initiatives such as ELLIS and Data Science Africa.

7. Addressing the Innovation Supply Chain

Industry Engagement

• Challenge: Connecting academic innovation to industry needs.
• ai@cam’s Approach:
  • Collaborate with Strategic Partnerships Office to develop industrial partnerships.
  • Plan for an innovation initiative (sciencepreneurship at Cambridge) to bridge academic research and entrepreneurship.

Innovation Economy Conclusion