Neil Lawrence's Talks
edit

AI needs to serve people, science, and society

• ,

$$\newcommand{\tk}[1]{} \newcommand{\Amatrix}{\mathbf{A}} \newcommand{\KL}[2]{\text{KL}\left( #1\,\|\,#2 \right)} \newcommand{\Kaast}{\kernelMatrix_{\mathbf{ \ast}\mathbf{ \ast}}} \newcommand{\Kastu}{\kernelMatrix_{\mathbf{ \ast} \inducingVector}} \newcommand{\Kff}{\kernelMatrix_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\Kfu}{\kernelMatrix_{\mappingFunctionVector \inducingVector}} \newcommand{\Kuast}{\kernelMatrix_{\inducingVector \bf\ast}} \newcommand{\Kuf}{\kernelMatrix_{\inducingVector \mappingFunctionVector}} \newcommand{\Kuu}{\kernelMatrix_{\inducingVector \inducingVector}} \newcommand{\Kuui}{\Kuu^{-1}} \newcommand{\Qaast}{\mathbf{Q}_{\bf \ast \ast}} \newcommand{\Qastf}{\mathbf{Q}_{\ast \mappingFunction}} \newcommand{\Qfast}{\mathbf{Q}_{\mappingFunctionVector \bf \ast}} \newcommand{\Qff}{\mathbf{Q}_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\aMatrix}{\mathbf{A}} \newcommand{\aScalar}{a} \newcommand{\aVector}{\mathbf{a}} \newcommand{\acceleration}{a} \newcommand{\bMatrix}{\mathbf{B}} \newcommand{\bScalar}{b} \newcommand{\bVector}{\mathbf{b}} \newcommand{\basisFunc}{\phi} \newcommand{\basisFuncVector}{\boldsymbol{ \basisFunc}} \newcommand{\basisFunction}{\phi} \newcommand{\basisLocation}{\mu} \newcommand{\basisMatrix}{\boldsymbol{ \Phi}} \newcommand{\basisScalar}{\basisFunction} \newcommand{\basisVector}{\boldsymbol{ \basisFunction}} \newcommand{\activationFunction}{\phi} \newcommand{\activationMatrix}{\boldsymbol{ \Phi}} \newcommand{\activationScalar}{\basisFunction} \newcommand{\activationVector}{\boldsymbol{ \basisFunction}} \newcommand{\bigO}{\mathcal{O}} \newcommand{\binomProb}{\pi} \newcommand{\cMatrix}{\mathbf{C}} \newcommand{\cbasisMatrix}{\hat{\boldsymbol{ \Phi}}} \newcommand{\cdataMatrix}{\hat{\dataMatrix}} \newcommand{\cdataScalar}{\hat{\dataScalar}} \newcommand{\cdataVector}{\hat{\dataVector}} \newcommand{\centeredKernelMatrix}{\mathbf{ \MakeUppercase{\centeredKernelScalar}}} \newcommand{\centeredKernelScalar}{b} \newcommand{\centeredKernelVector}{\centeredKernelScalar} \newcommand{\centeringMatrix}{\mathbf{H}} \newcommand{\chiSquaredDist}[2]{\chi_{#1}^{2}\left(#2\right)} \newcommand{\chiSquaredSamp}[1]{\chi_{#1}^{2}} \newcommand{\conditionalCovariance}{\boldsymbol{ \Sigma}} \newcommand{\coregionalizationMatrix}{\mathbf{B}} \newcommand{\coregionalizationScalar}{b} \newcommand{\coregionalizationVector}{\mathbf{ \coregionalizationScalar}} \newcommand{\covDist}[2]{\text{cov}_{#2}\left(#1\right)} \newcommand{\covSamp}[1]{\text{cov}\left(#1\right)} \newcommand{\covarianceScalar}{c} \newcommand{\covarianceVector}{\mathbf{ \covarianceScalar}} \newcommand{\covarianceMatrix}{\mathbf{C}} \newcommand{\covarianceMatrixTwo}{\boldsymbol{ \Sigma}} \newcommand{\croupierScalar}{s} \newcommand{\croupierVector}{\mathbf{ \croupierScalar}} \newcommand{\croupierMatrix}{\mathbf{ \MakeUppercase{\croupierScalar}}} \newcommand{\dataDim}{p} \newcommand{\dataIndex}{i} \newcommand{\dataIndexTwo}{j} \newcommand{\dataMatrix}{\mathbf{Y}} \newcommand{\dataScalar}{y} \newcommand{\dataSet}{\mathcal{D}} \newcommand{\dataStd}{\sigma} \newcommand{\dataVector}{\mathbf{ \dataScalar}} \newcommand{\decayRate}{d} \newcommand{\degreeMatrix}{\mathbf{ \MakeUppercase{\degreeScalar}}} \newcommand{\degreeScalar}{d} \newcommand{\degreeVector}{\mathbf{ \degreeScalar}} \newcommand{\diag}[1]{\text{diag}\left(#1\right)} \newcommand{\diagonalMatrix}{\mathbf{D}} \newcommand{\diff}[2]{\frac{\text{d}#1}{\text{d}#2}} \newcommand{\diffTwo}[2]{\frac{\text{d}^2#1}{\text{d}#2^2}} \newcommand{\displacement}{x} \newcommand{\displacementVector}{\textbf{\displacement}} \newcommand{\distanceMatrix}{\mathbf{ \MakeUppercase{\distanceScalar}}} \newcommand{\distanceScalar}{d} \newcommand{\distanceVector}{\mathbf{ \distanceScalar}} \newcommand{\eigenvaltwo}{\ell} \newcommand{\eigenvaltwoMatrix}{\mathbf{L}} \newcommand{\eigenvaltwoVector}{\mathbf{l}} \newcommand{\eigenvalue}{\lambda} \newcommand{\eigenvalueMatrix}{\boldsymbol{ \Lambda}} \newcommand{\eigenvalueVector}{\boldsymbol{ \lambda}} \newcommand{\eigenvector}{\mathbf{ \eigenvectorScalar}} \newcommand{\eigenvectorMatrix}{\mathbf{U}} \newcommand{\eigenvectorScalar}{u} \newcommand{\eigenvectwo}{\mathbf{v}} \newcommand{\eigenvectwoMatrix}{\mathbf{V}} \newcommand{\eigenvectwoScalar}{v} \newcommand{\entropy}[1]{\mathcal{H}\left(#1\right)} \newcommand{\errorFunction}{E} \newcommand{\expDist}[2]{\left\langle#1\right\rangle_{#2}} \newcommand{\expSamp}[1]{\left\langle#1\right\rangle} \newcommand{\expectation}[1]{\left\langle #1 \right\rangle } \newcommand{\expectationDist}[2]{\left\langle #1 \right\rangle _{#2}} \newcommand{\expectedDistanceMatrix}{\mathcal{D}} \newcommand{\eye}{\mathbf{I}} \newcommand{\fantasyDim}{r} \newcommand{\fantasyMatrix}{\mathbf{ \MakeUppercase{\fantasyScalar}}} \newcommand{\fantasyScalar}{z} \newcommand{\fantasyVector}{\mathbf{ \fantasyScalar}} \newcommand{\featureStd}{\varsigma} \newcommand{\gammaCdf}[3]{\mathcal{GAMMA CDF}\left(#1|#2,#3\right)} \newcommand{\gammaDist}[3]{\mathcal{G}\left(#1|#2,#3\right)} \newcommand{\gammaSamp}[2]{\mathcal{G}\left(#1,#2\right)} \newcommand{\gaussianDist}[3]{\mathcal{N}\left(#1|#2,#3\right)} \newcommand{\gaussianSamp}[2]{\mathcal{N}\left(#1,#2\right)} \newcommand{\uniformDist}[3]{\mathcal{U}\left(#1|#2,#3\right)} \newcommand{\uniformSamp}[2]{\mathcal{U}\left(#1,#2\right)} \newcommand{\given}{|} \newcommand{\half}{\frac{1}{2}} \newcommand{\heaviside}{H} \newcommand{\hiddenMatrix}{\mathbf{ \MakeUppercase{\hiddenScalar}}} \newcommand{\hiddenScalar}{h} \newcommand{\hiddenVector}{\mathbf{ \hiddenScalar}} \newcommand{\identityMatrix}{\eye} \newcommand{\inducingInputScalar}{z} \newcommand{\inducingInputVector}{\mathbf{ \inducingInputScalar}} \newcommand{\inducingInputMatrix}{\mathbf{Z}} \newcommand{\inducingScalar}{u} \newcommand{\inducingVector}{\mathbf{ \inducingScalar}} \newcommand{\inducingMatrix}{\mathbf{U}} \newcommand{\inlineDiff}[2]{\text{d}#1/\text{d}#2} \newcommand{\inputDim}{q} \newcommand{\inputMatrix}{\mathbf{X}} \newcommand{\inputScalar}{x} \newcommand{\inputSpace}{\mathcal{X}} \newcommand{\inputVals}{\inputVector} \newcommand{\inputVector}{\mathbf{ \inputScalar}} \newcommand{\iterNum}{k} \newcommand{\kernel}{\kernelScalar} \newcommand{\kernelMatrix}{\mathbf{K}} \newcommand{\kernelScalar}{k} \newcommand{\kernelVector}{\mathbf{ \kernelScalar}} \newcommand{\kff}{\kernelScalar_{\mappingFunction \mappingFunction}} \newcommand{\kfu}{\kernelVector_{\mappingFunction \inducingScalar}} \newcommand{\kuf}{\kernelVector_{\inducingScalar \mappingFunction}} \newcommand{\kuu}{\kernelVector_{\inducingScalar \inducingScalar}} \newcommand{\lagrangeMultiplier}{\lambda} \newcommand{\lagrangeMultiplierMatrix}{\boldsymbol{ \Lambda}} \newcommand{\lagrangian}{L} \newcommand{\laplacianFactor}{\mathbf{ \MakeUppercase{\laplacianFactorScalar}}} \newcommand{\laplacianFactorScalar}{m} \newcommand{\laplacianFactorVector}{\mathbf{ \laplacianFactorScalar}} \newcommand{\laplacianMatrix}{\mathbf{L}} \newcommand{\laplacianScalar}{\ell} \newcommand{\laplacianVector}{\mathbf{ \ell}} \newcommand{\latentDim}{q} \newcommand{\latentDistanceMatrix}{\boldsymbol{ \Delta}} \newcommand{\latentDistanceScalar}{\delta} \newcommand{\latentDistanceVector}{\boldsymbol{ \delta}} \newcommand{\latentForce}{f} \newcommand{\latentFunction}{u} \newcommand{\latentFunctionVector}{\mathbf{ \latentFunction}} \newcommand{\latentFunctionMatrix}{\mathbf{ \MakeUppercase{\latentFunction}}} \newcommand{\latentIndex}{j} \newcommand{\latentScalar}{z} \newcommand{\latentVector}{\mathbf{ \latentScalar}} \newcommand{\latentMatrix}{\mathbf{Z}} \newcommand{\learnRate}{\eta} \newcommand{\lengthScale}{\ell} \newcommand{\rbfWidth}{\ell} \newcommand{\likelihoodBound}{\mathcal{L}} \newcommand{\likelihoodFunction}{L} \newcommand{\locationScalar}{\mu} \newcommand{\locationVector}{\boldsymbol{ \locationScalar}} \newcommand{\locationMatrix}{\mathbf{M}} \newcommand{\variance}[1]{\text{var}\left( #1 \right)} \newcommand{\mappingFunction}{f} \newcommand{\mappingFunctionMatrix}{\mathbf{F}} \newcommand{\mappingFunctionTwo}{g} \newcommand{\mappingFunctionTwoMatrix}{\mathbf{G}} \newcommand{\mappingFunctionTwoVector}{\mathbf{ \mappingFunctionTwo}} \newcommand{\mappingFunctionVector}{\mathbf{ \mappingFunction}} \newcommand{\scaleScalar}{s} \newcommand{\mappingScalar}{w} \newcommand{\mappingVector}{\mathbf{ \mappingScalar}} \newcommand{\mappingMatrix}{\mathbf{W}} \newcommand{\mappingScalarTwo}{v} \newcommand{\mappingVectorTwo}{\mathbf{ \mappingScalarTwo}} \newcommand{\mappingMatrixTwo}{\mathbf{V}} \newcommand{\maxIters}{K} \newcommand{\meanMatrix}{\mathbf{M}} \newcommand{\meanScalar}{\mu} \newcommand{\meanTwoMatrix}{\mathbf{M}} \newcommand{\meanTwoScalar}{m} \newcommand{\meanTwoVector}{\mathbf{ \meanTwoScalar}} \newcommand{\meanVector}{\boldsymbol{ \meanScalar}} \newcommand{\mrnaConcentration}{m} \newcommand{\naturalFrequency}{\omega} \newcommand{\neighborhood}[1]{\mathcal{N}\left( #1 \right)} \newcommand{\neilurl}{http://inverseprobability.com/} \newcommand{\noiseMatrix}{\boldsymbol{ E}} \newcommand{\noiseScalar}{\epsilon} \newcommand{\noiseVector}{\boldsymbol{ \epsilon}} \newcommand{\noiseStd}{\sigma} \newcommand{\norm}[1]{\left\Vert #1 \right\Vert} \newcommand{\normalizedLaplacianMatrix}{\hat{\mathbf{L}}} \newcommand{\normalizedLaplacianScalar}{\hat{\ell}} \newcommand{\normalizedLaplacianVector}{\hat{\mathbf{ \ell}}} \newcommand{\numActive}{m} \newcommand{\numBasisFunc}{m} \newcommand{\numComponents}{m} \newcommand{\numComps}{K} \newcommand{\numData}{n} \newcommand{\numFeatures}{K} \newcommand{\numHidden}{h} \newcommand{\numInducing}{m} \newcommand{\numLayers}{\ell} \newcommand{\numNeighbors}{K} \newcommand{\numSequences}{s} \newcommand{\numSuccess}{s} \newcommand{\numTasks}{m} \newcommand{\numTime}{T} \newcommand{\numTrials}{S} \newcommand{\outputIndex}{j} \newcommand{\paramVector}{\boldsymbol{ \theta}} \newcommand{\parameterMatrix}{\boldsymbol{ \Theta}} \newcommand{\parameterScalar}{\theta} \newcommand{\parameterVector}{\boldsymbol{ \parameterScalar}} \newcommand{\partDiff}[2]{\frac{\partial#1}{\partial#2}} \newcommand{\precisionScalar}{j} \newcommand{\precisionVector}{\mathbf{ \precisionScalar}} \newcommand{\precisionMatrix}{\mathbf{J}} \newcommand{\pseudotargetScalar}{\widetilde{y}} \newcommand{\pseudotargetVector}{\mathbf{ \pseudotargetScalar}} \newcommand{\pseudotargetMatrix}{\mathbf{ \widetilde{Y}}} \newcommand{\rank}[1]{\text{rank}\left(#1\right)} \newcommand{\rayleighDist}[2]{\mathcal{R}\left(#1|#2\right)} \newcommand{\rayleighSamp}[1]{\mathcal{R}\left(#1\right)} \newcommand{\responsibility}{r} \newcommand{\rotationScalar}{r} \newcommand{\rotationVector}{\mathbf{ \rotationScalar}} \newcommand{\rotationMatrix}{\mathbf{R}} \newcommand{\sampleCovScalar}{s} \newcommand{\sampleCovVector}{\mathbf{ \sampleCovScalar}} \newcommand{\sampleCovMatrix}{\mathbf{s}} \newcommand{\scalarProduct}[2]{\left\langle{#1},{#2}\right\rangle} \newcommand{\sign}[1]{\text{sign}\left(#1\right)} \newcommand{\sigmoid}[1]{\sigma\left(#1\right)} \newcommand{\singularvalue}{\ell} \newcommand{\singularvalueMatrix}{\mathbf{L}} \newcommand{\singularvalueVector}{\mathbf{l}} \newcommand{\sorth}{\mathbf{u}} \newcommand{\spar}{\lambda} \newcommand{\trace}[1]{\text{tr}\left(#1\right)} \newcommand{\BasalRate}{B} \newcommand{\DampingCoefficient}{C} \newcommand{\DecayRate}{D} \newcommand{\Displacement}{X} \newcommand{\LatentForce}{F} \newcommand{\Mass}{M} \newcommand{\Sensitivity}{S} \newcommand{\basalRate}{b} \newcommand{\dampingCoefficient}{c} \newcommand{\mass}{m} \newcommand{\sensitivity}{s} \newcommand{\springScalar}{\kappa} \newcommand{\springVector}{\boldsymbol{ \kappa}} \newcommand{\springMatrix}{\boldsymbol{ \mathcal{K}}} \newcommand{\tfConcentration}{p} \newcommand{\tfDecayRate}{\delta} \newcommand{\tfMrnaConcentration}{f} \newcommand{\tfVector}{\mathbf{ \tfConcentration}} \newcommand{\velocity}{v} \newcommand{\sufficientStatsScalar}{g} \newcommand{\sufficientStatsVector}{\mathbf{ \sufficientStatsScalar}} \newcommand{\sufficientStatsMatrix}{\mathbf{G}} \newcommand{\switchScalar}{s} \newcommand{\switchVector}{\mathbf{ \switchScalar}} \newcommand{\switchMatrix}{\mathbf{S}} \newcommand{\tr}[1]{\text{tr}\left(#1\right)} \newcommand{\loneNorm}[1]{\left\Vert #1 \right\Vert_1} \newcommand{\ltwoNorm}[1]{\left\Vert #1 \right\Vert_2} \newcommand{\onenorm}[1]{\left\vert#1\right\vert_1} \newcommand{\twonorm}[1]{\left\Vert #1 \right\Vert} \newcommand{\vScalar}{v} \newcommand{\vVector}{\mathbf{v}} \newcommand{\vMatrix}{\mathbf{V}} \newcommand{\varianceDist}[2]{\text{var}_{#2}\left( #1 \right)} \newcommand{\vecb}[1]{\left(#1\right):} \newcommand{\weightScalar}{w} \newcommand{\weightVector}{\mathbf{ \weightScalar}} \newcommand{\weightMatrix}{\mathbf{W}} \newcommand{\weightedAdjacencyMatrix}{\mathbf{A}} \newcommand{\weightedAdjacencyScalar}{a} \newcommand{\weightedAdjacencyVector}{\mathbf{ \weightedAdjacencyScalar}} \newcommand{\onesVector}{\mathbf{1}} \newcommand{\zerosVector}{\mathbf{0}} $$
at Digitalisation and AI for public value on Jun 4, 2024 [reveal]
Neil D. Lawrence, University of Cambridge
Jessica Montgomery

Abstract

Artificial intelligence offers great promise, but we must ensure it does not deepen inequalities. In this provocation we will argue that AI hasn’t delivered on what society has asked of it, but it new technologies mean it could do.

Henry Ford’s Faster Horse

[edit]

Figure: A 1925 Ford Model T built at Henry Ford’s Highland Park Plant in Dearborn, Michigan. This example now resides in Australia, owned by the founder of FordModelT.net. From https://commons.wikimedia.org/wiki/File:1925_Ford_Model_T_touring.jpg

It’s said that Henry Ford’s customers wanted a “a faster horse”. If Henry Ford was selling us artificial intelligence today, what would the customer call for, “a smarter human”? That’s certainly the picture of machine intelligence we find in science fiction narratives, but the reality of what we’ve developed is much more mundane.

Car engines produce prodigious power from petrol. Machine intelligences deliver decisions derived from data. In both cases the scale of consumption enables a speed of operation that is far beyond the capabilities of their natural counterparts. Unfettered energy consumption has consequences in the form of climate change. Does unbridled data consumption also have consequences for us?

If we devolve decision making to machines, we depend on those machines to accommodate our needs. If we don’t understand how those machines operate, we lose control over our destiny. Our mistake has been to see machine intelligence as a reflection of our intelligence. We cannot understand the smarter human without understanding the human. To understand the machine, we need to better understand ourselves.

The Atomic Human

[edit]

Figure: The Atomic Eye, by slicing away aspects of the human that we used to believe to be unique to us, but are now the preserve of the machine, we learn something about what it means to be human.

In Greek mythology, Panacea was the goddess of the universal remedy. One consequence of the pervasive potential of AI is that it is positioned, like Panacea, as the purveyor of a universal solution. Whether it is overcoming industry’s productivity challenges, or as a salve for strained public sector services, or a remedy for pressing global challenges in sustainable development, AI is presented as an elixir to resolve society’s problems.

In practice, translation of AI technology into practical benefit is not simple. Moreover, a growing body of evidence shows that risks and benefits from AI innovations are unevenly distributed across society.

When carelessly deployed, AI risks exacerbating existing social and economic inequalities.

Revolution

[edit]

Arguably the information revolution we are experiencing is unprecedented in history. But changes in the way we share information have a long history. Over 5,000 years ago in the city of Uruk, on the banks of the Euphrates, communities which relied on the water to irrigate their corps developed an approach to recording transactions in clay. Eventually the system of recording system became sophisticated enough that their oral histories could be recorded in the form of the first epic: Gilgamesh.

See Lawrence (2024) cuneiform p. 337, 360, 390.

Figure: Chicago Stone, side 2, recording sale of a number of fields, probably from Isin, Early Dynastic Period, c. 2600 BC, black basalt

It was initially developed for people as a record of who owed what to whom, expanding individuals’ capacity to remember. But over a five hundred year period writing evolved to become a tool for literature as well. More pithily put, writing was invented by accountants not poets (see e.g. this piece by Tim Harford).

In some respects today’s revolution is different, because it involves also the creation of stories as well as their curation. But in some fundamental ways we can see what we have produced as another tool for us in the information revolution.

Coin Pusher

[edit]

Disruption of society is like a coin pusher, it’s those who are already on the edge who are most likely to be effected by disruption.

Figure: A coin pusher is a game where coins are dropped into th etop of the machine, and they disrupt those on the existing steps. With any coin drop, many coins move, but it is those on the edge, who are often only indirectly effected, but also most traumatically effected by the change.

One danger of the current hype around ChatGPT is that we are overly focussing on the fact that it seems to have significant effect on professional jobs, people are naturally asking the question “what does it do for my role?”. No doubt, there will be disruption, but the coin pusher hypothesis suggests that that disruption will likely involve movement on the same step. However it is those on the edge already, who are often not working directly in the information economy, who often have less of a voice in the policy conversation who are likely to be most disrupted.

Royal Society Report

[edit]

Figure: The Royal Society report on Machine Learning was released on 25th April 2017

A useful reference for state of the art in machine learning is the UK Royal Society Report, Machine Learning: Power and Promise of Computers that Learn by Example.

See Lawrence (2024) Royal Society; machine learning review and p. 25, 321, 395.

Public Research

[edit]

Figure: The Royal Society comissioned public research from Mori as part of the machine learning review.

As is often the cas when members of the public are well convened, they offered sensible opinions about the utility and challenges of machine learning methods.

Figure: One of the questions focussed on machine learning applications.

A range of different scenaios were captured by this qualitative work.

Figure: The public were broadly supportive of a range of application areas.

Figure: But they failed to see the point in AI’s that could produce poetry.

The one scenario where the public were unable to perceive any advantage in machine learning was an example from art, the creation of poetry. This was felt to be a fundamentally human activity that machines could only emulate at best.

Mercutio

[edit]

It’s ironic that despite the public focus on transport, health, cities, crime and their confusion as to why we might want AI to do art, one area where significant progress has been made is on AIs that can create literature.

Figure: Despite the public’s desire to see challenges in health, finance, transport, crime solved by machine learning and their skepticism around poetry, one of the problems we have solved seems to be poetry.

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

[edit]

In Baroness Onora O’Neill’s Reeith Lectures from 2002, she raises the challenge of trust. There are many aspects to her arcuments, but one of the key points she makes is that we cannot trust without the notion of duty. O’Neill is bemoaning the substitution of duty with process. The idea is that processes and transparency are supposed to hold us to account by measuring outcomes. But these processes themselves overwhelm decision makers and undermine their professional duty to deliver the right outcome.

Figure: A Question of Trust by Onora O’Neil which examines the nature of trust and its role in society.

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)]

O’Neill is speaking in 2002, in the early days of the internet and before social media. Much of her thoughts are even more relevant for today than they were when she spoke. This is because the increased availability of information and machine driven decision-making makes the mistaken premise, that process is an adequate substitute for duty, more apparently plausible. But this undermines what O’Neill calls “intelligent accountability”, which is not accounting by the numbers, but through professional education and institutional safeguards.

See Lawrence (2024) O’Neill, Baroness Onora: ‘A question of trust’ lecture series (2002) p. 352, 363.

The Open Society and its Enemies

[edit]

Figure: The Open Society and Its Enemies by Karl Popper views liberal democracies as a collection of “piecemeal social engineers” who strive towards better outcomes.

Popper opened the preface to his book (Popper, 1945) with the following words:

If in this book harsh words are spoken about some of the greatest among the intellectual leaders of mankind, my motive is not, I hope, to belittle them. It springs rather from my conviction that, if our civilization is to survive, we must break with the habit of deference to great men. Great men may make great mistakes; and as the book tries to show, some of the greatest leaders of the past supported the perennial attack on freedom and reason.

He had written the book against the background of the second world war, his decision to write it taken on the day the Nazis invaded Austria in March 1938. His book is a reaction to totalitarianism.

For Popper, the ideas of “great men” become totalitarian when imposed on society. He advocates for direct liberal democracy as the only form of government that can allow for institutional change without bloodshed. The open society is one characterized by institutions and individuals that can engage in the practical pursuit of solutions to social and political problems. The institutions are also underpinned by individuals: lawyers, accountants, civil administrators and many more. To Popper it is these “piecemeal social engineers” who offer pragmatic solutions to our society’s political and social challenges.

See Lawrence (2024) Popper, Karl The Open Society and its Enemies p. 371–374.

The Atomic Human

[edit]

Figure: The Atomic Human (Lawrence, 2024) due for release in June 2024.

Thanks!

For more information on these subjects and more you might want to check the following resources.

References

Lawrence, N.D., 2024. The atomic human: Understanding ourselves in the age of AI. Allen Lane.
O’Neill, O., 2002. A question of trust. Cambridge University Press.
Popper, K.R., 1945. The open society and its enemies. Routledge.