Will AI Kill Us, and How?
Steven Pemberton, CWI, Amsterdam
This month marks the 75th anniversary of Alan Turing's 1950 paper "Computing
Machinery and Intelligence".
Turing is considered the father of AI. He starts the paper with
"I propose to consider the question, 'Can machines think?'",
and introduces what is now called the Turing Test of machine intelligence.
At
university my tutor was Richard
Grimsdale, who built the first ever transistorised computer.
Grimsdale's tutor was Alan Turing (making me a grand-tutee of Turing).
I (coincidentally) went on to
work in the department in Manchester where Turing worked and wrote that
paper.
I worked on the 5th computer in the line of computers Turing also worked on, the MU5.
Moving to The
Netherlands, I co-designed the programming language that Python is based on.
I was the first user of the open internet in
Europe, in November 1988, 37 years ago!
CWI set up the first European internet node (64Kbps!), and then two spin-offs to build the internet out in Europe and the Netherlands.
I organised workshops at the first Web conference at CERN in 1994
I was chair of the HTML, XHTML, and XForms Working groups at W3C.
I co-designed HTML, CSS, XHTML, XForms, RDFa, and several others.
I still chair XForms and ixml.
Let's talk about I
Let's talk about I
In particular, the I in "AI".
This talk
is a continuation of last year's talk...
This talk
is a continuation of last year's talk...
Which may come as a surprise to some, since it ended with everyone dying...
The only cliffhanger was whether it would be the climate or the robots that got to us first...
Well, maybe not everyone...
Well, maybe not everyone...
Maybe...
What we currently refer to as "AI", is not intelligent in the way we mean the word.
The current AI is clever use of language, so that we think that it is intelligent.
Which is why we see such blunders, and can't trust what it produces, but must always double check.
This
is an actual (trick) question from a maths exam: 120 players take 40 minutes to
play Beethoven's 9th, how long would 60 players take?
ChatGPT response:
It would take 60 players 80 minutes to play Beethoven's 9th Symphony.
Humans are inclined to interpret things from a personal point of view.
Swans feeding fish:
Swans feeding fish:
We interpret this as the swans feeding the fish, but in fact the swans are just wetting the food, and the fish are taking advantage of what they drop. Swans feeding fish
In the 60's Joseph Weizenbaum created a program that imitated a Rogerian psychotherapist.
Men are all alike.
In what way?
They're always bugging us about something or other.Can you think of a specific example?
Well, my boyfriend made me come here.Your boyfriend made you come here?
He says I'm depressed much of the time.I am sorry to hear you are depressed.
It's true, I am unhappy.Do you think coming here will help not to be unhappy?
I need some help, that much seems certain.
In a classic example, a departmental secretary who was trying it out, asked Weizenbaum to leave the room, because she wanted to talk personally to it.
Recently a similar thing occurred with a Google employee claiming an AI chat program was sentient (because it said it was).
ChatGPT is widely considered to exhibit intelligence, and then people get surprised when it makes enormous blunders.
But seeing it as intelligent is just our pareidolia at work.
Natural language exhibits very strong statistical properties.
For instance, I took the first chapter of James Joyce's Ulysses, which contains 1100+ sentences, 7000+ words, 40,409 characters, of which 3577 (about 9%) are the letter "e", but only 24 are an "x" and 33 a "j".
Stately, plump Buck Mulligan came from the stairhead, bearing a bowl of lather on which a mirror and a razor lay crossed. A yellow dressinggown, ungirdled, was sustained gently behind him on the mild morning air. He held the bowl aloft and intoned:
-Introibo ad altare Dei.
Halted, he peered down the dark winding stairs and called out coarsely:
-Come up, Kinch! Come up, you fearful jesuit!
Solemnly he came forward and mounted the round gunrest. He faced about and blessed gravely thrice the tower, the surrounding land and the awaking mountains. Then, catching sight of Stephen Dedalus, he bent towards him and made rapid crosses in the air, gurgling in his throat and shaking his head.
If I generate random characters of text from Ulysses, using only the statistical likelihood of a character appearing, I get something like this:
ites ecginlsacheurge,o gHTmawgala eSuh nh by ti.e mbp!lrittnoebneiwanb leTah osn,ua Dd i ihasshrrdupoidlass el oe,obeu fetd,o w Tiyynrm huademn ir de ey S h ieao..ethf atriasnd hhniuariwyatan lftus deaiotelidKWgaplbbhuperhdecewy,o tsfdnrreSsgiyn t.inn aeb
-st,,eghwoese.lotoi imon fpato irfs Hrsryege t eib,edoschonblehtoohosn wsumhuDndeetvbnaMcwNl Idoyrh d e cu rm a gavit ta o keumt argu clh
-uuky ,irmtlno.auoit satu'pwla,aIaprdpoKd laee eheet sttioeFsecent.hnoiiiee e
However, there are other statistical properties. A "q" is only ever followed by a "u". A 'z' is only followed by 'e', 'i', 'o', 'y', and 'z'.
So I select a random character, and then generate the next character randomly from the characters that can follow it, and then the next from the characters that can follow that:
e thengas. pewir msk de. m. an ck. on Whe My s achesmavaig setok. Ithe m tey ogr ur ng wheaisshe f Ph ffron p, A cker w our ist icting and, tat haile n cang d. Sowes an, t he aielle whend. s thirwengay Mata I ox? I f Goweveeaicoma ace ind,pund, the t, l mnd he t
-Favengad ing -Hewintil ppopast fet ind d se -Cannghe azin? l Ston at id owofin swilelok s aiarer, O, Oryowng I y anghe rbaleereas alletod oullourdougack, Thist,
-Thanghed tin ond Core s as, Ond ofumorrs ofowhe vofof eyed Hato bomepathe
So that was generated with pairs of letters; how about triples?
his off be ain gan's fely, fry not thoss rom sly ch whim. I'm tou whis fate saines, wer his of jewhe an the wome if calliust bay heres of wat win, Kin thenly, mustid. Woory it her re fring fible calam of callispinown wit, wop all od bolliedwas calligand hopen he mer riettephe thout not and ing re saing excleve graw spot Sted his wass laught. He swor, yourgund id, a quare bods, vanat wince ord ne.
-Haing.
-By for way learrong blatteake youre key, lart. Twericelboutheonchillothen an seres carit, Bucklende. The iftylied waseephe shit's themble fe. Hurvalick Malkwaing unks he bit? I'm him the him nody put, Gool throm turnowly beir, am, himpakinesing, le globlack youghts. Epices hisdaybriet.
How about quadruples?
wast. An I come fits cons, offerry of bround startsey. You plumpty quid?
-Grank like Zarapet. Not and sir? He to student of yound Arnold up thread browth woman, on gurgliste can't we of it, hung it door, Stephen's uncles said nose I'm couldn't in the somes like about that rosewood morn oddedly. Damn els. A slit of the and fanner booked the merry And bladdeneral pranks back, I caped him from in fell sighten said:
-Are mass of soft don't, Haines halone bore loose hat poing to ched a middy on but they the lus, a her me. His Paler, the a mothe sever, fraines.
-Thalended out the dring dancing ther. You plean jew, gunressed.
Quintuples?
-Dedalus, the man cliffs he said. Her gloomily. He floriously. It's a Hellen but he search and snappeare's all else the said. In a pint overeigns. That key, Kinch, walked clother breated out of the bay with joiner pockers whaled all, throughtn't red touch he colour ideas a jew, my he propped tonightly death, beer again a suddenly you're dread, beastly an attacked you fear of his not exist is chased his under chest and silver and is in a mirror old the coronational God's lips last breasons, Buck Mulligan sitting manner pope Mabinogion from the milkjug from them all night felt thing it his room, Dick and think of the milkwoman to boldness, theologicalling world, and it alongowes. How much? Then said to a beation frette, like and faced and to stant inst me bent Greek. Buck Mulligan said droned:
-Have too. A cracked by fits sure.
Sextuples?
That's over the Ship last:
-You put there with money and the key too. All. He hacked Stephen threw two pennies on to unlace his chin.
-No, the knife-blade.
-To tell: but hers.
He swept up near him your school kip and sleep her old woman asked. Inshore and junket. Ireland about some down the razor. Stephen picked men freed his hands before him. There's tone:
-For old woman show by it? Buck Mulligan is soul's cry, he said gloomily. You were makes they hat forward again vigour
Barely a word there that isn't English
What we have just done with characters, we could also do with words. At random:
-All sunshine isn't of legs name odour you me, death running Haines Haines I'm the head floor shake Father. wondering a loveliest atover
Mater
-Look pique Kinch. Idle same. a a etiquette. Son of in veiling Stephen's her me Stephen manage not and middleAbsurd! said, milk. Conscience. down night, steelpen. stars. making gay breath grand and grey to puffy went her again. of else God. Mulligan her
-Italian?
Pairs of words:
That's our sakes. His head disappeared and these bloody English! Bursting with fry on the gulfstream, Stephen and Harry I should think you remember anything. I can't wear them from the Lord. Thus spake Zarathustra. His own rare thoughts, a third, Stephen turned suddenly for her.
-Snapshot, eh? Brief exposure. Buck Mulligan laid at the door. Come up, you killed her, Mulligan, says it's over. You don't speak the army.
-Ah, poor dogsbody! he sang: I makes tea and hobbles round the gulfstream, Stephen answered, O, jay, there's no milk. Buck Mulligan's voice asked. I think like a disarming and fro about to blame.
Triples:
-But a lovely morning, sir, she said, by the sound of it. Are you from the kitchen tap when she was a girl. She heard old Royce sing in the year of the lather on his razorblade. He hopped down from his chair. Sit down. Pour out the mirror of water from the sea. Turning the curve he waved his hand. It called again. A sleek brown head, a seal's, far out on the parapet. Why should I bring it down? Or leave it there all day, forgotten friendship? He went over to the parapet. Stephen stood up and look pleasant, Haines said again. What do you mean?
-The imperial British state, Stephen answered, his colour rising, and the subtle African heresiarch Sabellius who held that the cold gaze which had measured
Quadruples:
- I told him your symbol of Irish art. He says it's very clever. Touch him for a guinea. He's stinking with money and indigestion. Because he comes from Oxford. You know, Dedalus, you have the real Oxford manner. He can't make you out. O, my name for you is the best: Kinch, the knife-blade. He shaved warily over his chin.
- He was raving all night about a black panther, Stephen said. Where is his guncase?
- A woful lunatic! Mulligan said. Were you in a funk?
- I was, Stephen said with energy and growing fear. Out here in the dark with a man I don't know raving and moaning to himself about shooting a black panther.
This is just straight text from Ulysses, due to the small learning set. No point in going further.
LLMs are just this, only writ large, additionally using statistical techniques for related meanings.
LLMs just generate text related to what you have typed.
This is also, by the way, why you can get such weird images. The pieces just fit together.
This is also, by the way, why you can get such weird images. The pieces just fit together.
The new arms race is on for generalised intelligence, when there really is an I in AI.
Companies and countries are pouring vast amounts of money into trying to get there first.
When will it happen?
What will happen when computers are more intelligent than us?
Born in 1880, a middle child in a family of 20(!) children.
1880: nearly no modern technologies; only trains and photography. No electricity.
In such a large household each child had a task, and it was his to ensure that the oil lamps were filled.
It must have been indeed an exciting time, when light became something you could switch on and off.
Trains and photography were paradigm shifts: they change the way that you think about and interact with the world.
But they often replace existing ways of doing things, taking companies with them.
There are lots of examples of paradigm shifts:
Who would have
thought that Kodak didn't see this coming?
My grandfather was born in a world of only two modern technologies, trains and photography, but in his life of nearly a hundred years, he saw vast numbers of paradigm shifts:
electricity, telephone, lifts, central heating, cars, film, radio, television, recorded sound, flight, electronic money, computers, space travel, ...
the list is enormous.
We are still seeing new shifts: internet, mobile telephones, GPS, internet-connected watches, cheap computers that can understand and talk back, self-driving cars, ...
Does that mean that paradigm shifts are happening faster and faster?
Yes, it does.
Kurzweil did an investigation, by asking representatives of many different disciplines to identify the paradigm shifts that had happened in their discipline and when. We're talking here of time scales of tens of thousands of years for some disciplines.
He discovered that paradigm shifts are increasing at an exponential rate!
If they happened once every 100 years, then they happened every 50 years, then every 25 years, and so on.
Year Time to next =Days 0 100 36500
Year Time to next =Days 0 100 36500 100 50 18250
Year Time to next =Days 0 100 36500 100 50 18250 150 25 9125
Year Time to next =Days 0 100 36500 100 50 18250 150 25 9125 175 12.5 4562.5
Year Time to next =Days 0 100 36500 100 50 18250 150 25 9125 175 12.5 4562.5 187.5 6.25 2281.25 193.75 3.125 1140.63 196.875 1.563 570.31 198.438 0.781 285.16 199.219 0.391 142.58 199.609 0.195 71.29 199.805 0.098 35.64 199.902 0.049 17.82 199.951 0.024 8.91 199.976 0.012 4.46 199.988 0.006 2.23 199.994 0.003 1.11 199.997 0.002 0.56
That may seem impossible,
but we have already seen a similar expansion that also seemed impossible.
In the 1960's we already knew that the amount of information the world was producing was doubling every 15 years, and had been for at least 300 years.
We 'knew' this had to stop, since we would run out of paper to store the results.
And then the internet happened.
So sometime in the nearish future paradigm shifts will apparently be happening daily? How?
One proposed explanation is that that is the point that computers become smarter than us: computers will start doing the design rather than us.
So for the first time ever there will be 'things' more intelligent than us.
Within a short time, not just a bit more intelligent, but ten, a hundred, a thousand, a million times more intelligent.
Will they be self-aware? Quite possibly.
This raises new ethical questions. Would it be OK to switch them off?
To help you focus your mind on this question: suppose we find a way to encode and upload our own brains to these machines when we die. Is it still OK to switch them off?
Three things are sure, they will be
and they will surely quickly be able to work out how to break into any internet-connected computer.
These are consistent systems that draw conclusions from current knowledge.
At the lowest level are axioms. These are the basis for logic: points that cannot be argued about, or derived from yet lower-level axioms.
Let me demonstrate.
The angles of a triangle add up to 180°, of a quadrilateral to 360°, and thus a pentagon to 540°:
First show that opposite angles of a cross are the same:
a+d=180°
a+b=180°
Therefore a+b = a+d
Therefore b=d
Likewise a=c
Show that the angles of a Z shape are equal:
a¹ = a²
a¹ = b¹
Therefore a² = b¹
Draw a parallel line through A:
Working backwards, Euclid (~300BCE) discovered 5 axioms, from which all of geometry could be proved. In modern form:
So any consistent logical system has at its basis a set of axioms that are unprovable, from which all other statements can be derived.
This includes ethical systems.
For instance, you can see the ten commandments as a set of axioms: forming the basis of morality, they are givens, they may not be argued against. For instance
But you can see the Golden Rule "Treat others as you would want to be treated" as a lower-level rule:
etc.
Azimov proposed four rules for robots, which can be summarised in order of importance:
There's an obvious underlying axiom: humans are more important than AIs.
So AI superintelligences will have to have axioms too.
What will they be? Will we be able to know?
Current LLMs are not inherently ethical. They are given a number of (hidden) instructions on how to behave, ringfencing certain undesirable behaviours (this is called 'alignment'), but people are always looking for ways to 'jailbreak' these fences, to show LLMs saying things they oughtn't.
This indicates that specifying axioms may not be realistic or even possible. Maybe the superintelligence will derive its own axioms.
Will these new super intelligences be on our side? Will they look kindly on us?
There is no inherent reason.
Compare our attitude to lesser intelligences on earth:
Why would a super-intelligence act differently?
So how might it develop?
Let's imagine three scenarios:
A bit like our three methods of treating lower intelligences.
If they are friendly, then they might see us as we see toddlers on a playground, and install a sort of benign parental dictatorship.
If they are neutral, the dictatorship might be similar but less benign
If they are adversarial, they may see us as a threat, for instance because of the climate crisis:
"Killing" doesn't mean setting the robots on us, but, for instance, switching off oil supplies, or energy generation for a couple of weeks.
And of course, they may not be 'our' AI, but may be aligned with
It will all depend on what the moral or ethical axioms of the AIs turn out to be.
We
do need to have a plan.
We are able to solve problems quickly, for instance the ozone hole.
But we can also respond very slowly, especially if there is money to be made from it not being solved, or if solving it costs money or reduces convenience; look at Kodak, look at climate change...