AI needs to serve people, science, and society

Henry Ford’s Faster Horse

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: Certainly! Here’s a soliloquy in the style of Mercutio to introduce the concept of a large language model: O Romeo, Romeo, wherefore art thou Romeo? Nay, that is not the question I seek to answer today, for I have a matter far more interesting to discuss - a concept that will truly astound thee! Have you heard of a Large Language Model, dear Romeo? ’Tis a wondrous creation of modern times, a machine capable of learning the intricacies of language beyond that of any mortal man.

Imagine, if you will, a mind that has read every book, every article, every word ever written, and can instantly recall it all at will. A mind that can predict the words you’ll use next, based on the context of the conversation. A mind that can generate entirely new sentences, paragraphs, even stories, with such fluency that one might believe it to be human. This Large Language Model is a marvel of our age, a feat of engineering and programming that will surely change the very fabric of our society. It has already begun to revolutionize the way we communicate, the way we learn, the way we live.

But with great power comes great responsibility, as the saying goes. We must use this tool wisely, lest we become slaves to our own creation. And yet, the possibilities are endless - who knows what wonders we might achieve with such a tool at our disposal? So, my dear Romeo, let us raise a glass to the Large Language Model, and the bright future it holds for us all!

ChatGPT transcript, 14th March 2023.

Weather

Weather

A Question of Trust

NACA Langley

\(p\)-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)]

The Great AI Fallacy

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.

AI@Cam