copy blog to gemini://
This commit is contained in:
@@ -0,0 +1,29 @@
|
||||
# Harari’s Sapiens on Religion
|
||||
|
||||
Published: 14 Jan 2024
|
||||
|
||||
I’ve been slowly re-reading Yuval Noah Harari’s 2014 classic, Sapiens, which apart from being ridiculously over-scoped and hilariously under-evidenced, is proving delightfully entertaining.
|
||||
|
||||
=> https://www.ynharari.com/book/sapiens-2
|
||||
|
||||
I’ve just finished chapter 12, covering the world history of all religion in thirty pages. Of course, at that level of brevity, there will be many deficiencies. But here’s some thoughts - not terribly well organised - which stand out to me.
|
||||
|
||||
Hurari generally assumes a materialist metaphysic (a problem which blights the book more generally). Nothing exists except physical stuff. This gives him severe tunnel vision. As a consequence of this restricting metaphysic, he is forced to adopt limiting accounts of what the role of religion is in world history, and therefore what religion is.
|
||||
|
||||
> The crucial historical role of religion has been to give superhuman legitimacy to all social orders and hierarchies. Religion can thus be defined as a system of human norms and values that is founded on a belief in a superhuman order. (p. 234)
|
||||
|
||||
It might seem a little unfair to criticise Harari for giving a materialist account of religion. Sapiens is, after all, a materialist world history.
|
||||
|
||||
But this account is just one extreme example of how that project, to give a materialist account of world history, will inevitably lack the metaphysical resources to really understand the human story.
|
||||
|
||||
On Harari’s view, any human enterprise which attempts to understand that which transcends direct human experience is at best an effort in imaginative story-telling. All scientific theory, theology, ethics and metaphysics either contorted out of all recognition into a pragmatic fiction or is cast to the flames.
|
||||
|
||||
In particular, it’s a view which is incapable of taking seriously some of the most important questions human beings have grappled with in the course of their history. Those who know me won’t be surprised at which ones I’m going to pick out: who was the being which made their covenant with Abraham? How is that promise being fulfilled? And who the heck was Jesus of Nazareth?
|
||||
|
||||
If Harari’s characterisation of religion is adequate - and the Abrahamic faiths come under that banner - then those questions are reduced to nothing more profound than Doctor Who fans arguing over ‘canon’. The question of who God is becomes a mere tool for the organisation of society, rather than a substantial and important question on a matter of fact.
|
||||
|
||||
This is a shortcoming for its own sake: a materialist account of religion cannot adequately account for the phenomenon of religion itself.
|
||||
|
||||
But it is also a shortcoming even by its own lights. Without giving serious consideration to the substantial matter of what Harari calls ‘religion’ (which, to his mind, includes the Abrahamic faiths, Hinduism, paganism, animism, Buddhism, Shintoism, Confucianism, capitalism, communism and Nazism), even the material facts are inexplicable. Why would, as Harari is keen to point out, out, people fight and die over and over again for a fiction?
|
||||
|
||||
The material facts themselves prove that ‘religion’ as he construes it is not window dressing to the real story of history. It cannot merely serve as a mechanism in the churning of material history. It is itself the centre of the story.
|
||||
@@ -0,0 +1,255 @@
|
||||
# EUHWC Toast to the Lassies 2024
|
||||
|
||||
At the EUHWC Burns meet in Ullapool last weekend, I had the last privilege of giving the Toast to the Lassies. Particularly for the benefit of those who weren’t there, here it is in full!
|
||||
|
||||
Published on: 29 Jan 2024
|
||||
|
||||
Had Burns, instead of his sweet bonnie Jean,
|
||||
his skills poetical for to mature
|
||||
had any one of our club’s lassies seen
|
||||
he would forever have remained obscure.
|
||||
If he had nothing but this box of worms
|
||||
Scotia would have been poorer, that I’m sure.
|
||||
Now none of us can claim to be a Burns,
|
||||
I’m no poetic master, still, I’ll have a punt,
|
||||
though let’s be clear, I’ll do it on my terms.
|
||||
I’ve everywhere avoided being blunt -
|
||||
politeness matters more than any schema -
|
||||
but it is hard when Isla’s such a cunt.
|
||||
It was a challenge to produce a terza rima
|
||||
I could recite withouten snoring;
|
||||
you’ve been so stiff I thought youse had oedema.
|
||||
The bother is this year is you’ll all been boring:
|
||||
no drugs, no sex, no gossiping or lies,
|
||||
no rock and roll, and hardly any whoring.
|
||||
But hey well, rules is rules, I’ve had to try!
|
||||
At least it can’t be worse than the reply.
|
||||
|
||||
I’ll start with Audrey, the club’s senior member,
|
||||
for if there’s something that I say which disconcerts her,
|
||||
it’s fine: the poor old girl, she won’t remember.
|
||||
She likes to let us think she’s a hard worker
|
||||
but we’re electing a third social sec…
|
||||
it’s pretty clear she’s just another shirker.
|
||||
This lady, half American, half Czech,
|
||||
for study, moved to Scotland for to do
|
||||
American history – really, what the heck?
|
||||
The club is so much louder thanks to you:
|
||||
impressive vocals for just five foot two.
|
||||
|
||||
That woman, Willow, reggles is bespeckled
|
||||
with her sickle and her fishing tackle
|
||||
shackled by the shins while she is heckled;
|
||||
the way that Willow waddles maks me cackle
|
||||
like a speckled jackal getting tickles,
|
||||
worth a shekel in the tabernacle;
|
||||
I chuckle muckle at her love of pickles
|
||||
which she wiggles when she has the heart
|
||||
while work for the Committee’s fickle trickles.
|
||||
Her modus operandi: you can’t rush art.
|
||||
Her reimbursements programme’s going great;
|
||||
any day now, she’ll maybe even start.
|
||||
She cannot walk without Audrey, her mate:
|
||||
I wonder when they’re going to consummate.
|
||||
|
||||
Although they make them pretty tough in Peebles,
|
||||
the thought of actually going up a peak
|
||||
fills Shona Lewis with the heeble-jeebles.
|
||||
New car? We miss your beautiful antique!
|
||||
How long before this one’s also up a creek?
|
||||
|
||||
Once there was a lass called Hannah Collier
|
||||
whom even hell below regarded nasty,
|
||||
deeply despised by all that dwells there.
|
||||
Dating’s proceeding slowly for our lassie;
|
||||
not far from giving up til she beguiles
|
||||
a hot Italian in Southsider: classy!
|
||||
At first, Michaelo seems to be all smiles
|
||||
till it transpires he’s one of Dante’s demons…
|
||||
I guess it’s back to posters of Harry Styles.
|
||||
One day you’ll get a decent boy, keep dreamin;
|
||||
somewhere there waits a handsome Mr Collier.
|
||||
Hopefully when she meets him she’ll no be steamin.
|
||||
Hannah, I’m not sure why you chose to maul your
|
||||
poor skeleton at Subway (she’s still tetchy)
|
||||
and then abandon what remains of all your
|
||||
dignity at Ryvoan with a Frenchie!
|
||||
I think he wishes that he never met ye.
|
||||
|
||||
And has a quiet Felicia e’er been seen?
|
||||
The energy she has is frankly wild.
|
||||
I’ve never seen a hillwalker so keen!
|
||||
Ssie ischt raschtlos und nie gelangweilt.
|
||||
She eats raw oats with soggy protein powder:
|
||||
a camping pot has ne’er been worse defiled.
|
||||
She uses what her Maker has endowed her
|
||||
with: her recorder skills are off the charts;
|
||||
youse think I’m joking, but I wouldn’t doubt her!
|
||||
This lass of the land of the Rot-Gold-Schwarz
|
||||
will soon depart, though long we might beseech you
|
||||
to stay. Of course, you’ll break all of our hearts,
|
||||
but mine most of all. Any time, Felicia,
|
||||
Creag Meagaidh calls, I know routes up the rear
|
||||
dark and under-explored that I can teach you!
|
||||
I won’t deny I think it’s rather queer
|
||||
the things you do with chickpeas, but no matter.
|
||||
You’re keen, you’re quick, you’re cool, that much is clear.
|
||||
In fact, I think you’d make a damn good faffer:
|
||||
swoop down on distilleries like the Luftwaffe.
|
||||
|
||||
And now we come to our girl Emily Topness!
|
||||
You’re keen for social sec. You’d suit the role
|
||||
because… I’m not quite sure, it’s embdy’s guess.
|
||||
We met your sister, and she was just as dull.
|
||||
No, please drone on about Icelandic soil!
|
||||
Poor Joe here down the front’s bored out his skull.
|
||||
And since I mentioned Joe – I hate to spoil
|
||||
it for you – but you’ve got the inferior Joe,
|
||||
by Jove, no joke, it’s Jock here’s got the style!
|
||||
Nah, write the boy a sonnet, get in the flow,
|
||||
Whatever you produce’ll beat by thrice
|
||||
your Masters thesis. What’d you got to show
|
||||
for months of hunting for the butterflies?
|
||||
‘There weren’t any.’ Oh, and have some sense,
|
||||
cos I’ve heard rumours – I assume they’re lies –
|
||||
you’ve called yourself the ‘poet in residence.’
|
||||
You know you can’t compete, drop the pretence.
|
||||
|
||||
Tereza was our gear sec for last year.
|
||||
She helped herself to stuff: that’s factual.
|
||||
Now when she asks to loan a bit club gear
|
||||
we have to ask her to provide collateral.
|
||||
She picked up tin whistle pretty sharp!
|
||||
Which is to say, she’s not a natural.
|
||||
She’s nowhere happier than under tarp
|
||||
gazing up at the moon and stars alone
|
||||
somewhere distant and remote like Glen Tarff.
|
||||
Now what to say about Lucy Ma-the-soooon....
|
||||
she likes… to faff… mm hmmm… well, moving on!
|
||||
|
||||
And now we come to Emilie the French.
|
||||
She seems to be nice on the trips we see her
|
||||
but my distrust of frogs will ne’er be quenched.
|
||||
Claims she’s a ‘pharmacist’? So she’s a dealer.
|
||||
Need some pills in a pinch? You call, she’s there
|
||||
at your door in her rally-approved four-wheeler.
|
||||
One question we have is, why are you here?
|
||||
Most folk are in uni, you’ve no refutin
|
||||
you were kicked out after second year!
|
||||
Now the Engineering grad, Sophia Newton.
|
||||
Your namesake, Isaac, was a man convicted,
|
||||
constructed calculus; but no computin,
|
||||
not even Isaac’s, could’ve e’er predicted
|
||||
you’d drop the Eng for creative writing!
|
||||
now that’s what I would call a self-inflicted
|
||||
inflection point! It must be quite enlightening,
|
||||
but that doesn’t excuse when you give us an earful.
|
||||
The blood boils in our veins, the rage heightening,
|
||||
and you’re an American, that makes me fearful.
|
||||
What’s your secret? You have us knackered!
|
||||
What are you on to always be so cheerful?
|
||||
Now we approach the topic of Merzbacher.
|
||||
Wait, she’s not here? Abandoned ship?
|
||||
She says she’s informatics: so she’s a hacker?
|
||||
She has strong views, she lets her anger rip.
|
||||
Poor George got an earful, full of future advice,
|
||||
but why hasn’t she been on another club trip?
|
||||
We’re cruel to focus on this list of vice;
|
||||
the fact remains: she’s headstrong and nice.
|
||||
|
||||
On Skye, a lady gave her poles to Sasha,
|
||||
which was really nice - I mean just the best -
|
||||
but Sasha really didn’t have to flash her.
|
||||
Quick history lesson: way back, RBS
|
||||
led the banking system to self-destruct
|
||||
and left taxpayers to pick up the mess.
|
||||
Since then, the name’s so irredeemably fucked
|
||||
they’ve had to ditch the brand once and for all.
|
||||
There’s one lassie who I need not instruct
|
||||
What, these days, the Royal Bank is called
|
||||
cos NatWest’s nasty history of scandal
|
||||
didn’t stop Booth from working there at all.
|
||||
Nothing motivates her more than to trample
|
||||
upon the working class. They set her free.
|
||||
She sank the pound quicker than the Belgrano,
|
||||
because ‘there is no such thing as society,’
|
||||
that’s how it is, is it? All right, I see.
|
||||
|
||||
Now, coming all the way from Glenmore Lodge,
|
||||
it’s Ellie’s turn! We have done what we can,
|
||||
although I’m scared what she’ll put in my squash.
|
||||
She wasn’t into Benji, but listen man,
|
||||
you’re lucky that you dodged her drunken benders.
|
||||
You’ll wake up in a tent in Kyrgystan,
|
||||
as for how you got there, no-one remembers,
|
||||
and if you’d known you’d be sleeping next to Ellie,
|
||||
you would’ve brought some fucking ear defenders.
|
||||
She’ll wrap you in bubblewrap, from your ears to your belly,
|
||||
cotton clothes for none, and no complaining,
|
||||
applying safety to the max, spare socks in your wellies.
|
||||
She’s always at her Mountain Leader training,
|
||||
practicing her night nav in the locale,
|
||||
pursuing QMDs - unless it’s raining.
|
||||
But some water should not scare our gal!
|
||||
She’s had much experience with the wet as of late:
|
||||
after all, she got on well with our navy pal.
|
||||
What was the age of that particular first mate?
|
||||
Older than your ex - always part of the plan?
|
||||
Ah, of course! He was a spry twenty-eight!
|
||||
Youth’s for the losers, let’s get you a real man,
|
||||
mature and rugged, but kind and astute?
|
||||
Just make sure he’s not as old as your gran.
|
||||
One request we all have is you ditch the uke:
|
||||
never have strings been pluckèd quite so shitely;
|
||||
we would all much rather be hit by a nuke.
|
||||
And please shut up about your nice society.
|
||||
We are all glad you had a fun summer,
|
||||
but bringing it up throws us right back to sobriety.
|
||||
To lose you of course would be a bummer:
|
||||
that is, for your carefully groomed newcomers.
|
||||
|
||||
Now time for the main woman, El Presidente!
|
||||
To here, it’s been like getting stones to bleed,
|
||||
but in Isla Burslem’s case we’ve material aplenty!
|
||||
As Holy Scripture says, ‘let those who lead
|
||||
well be worthy of double honour,’ so
|
||||
your bit is double length – it’s quite the screed!
|
||||
I’ll start off with her brilliant boyfriend – oh!
|
||||
Not boyfriend! Friend? To me this rather smacks
|
||||
of low commitment, but what do I know?
|
||||
So far, he’s disappointing, but on track.
|
||||
What’s he up to Isla: seven minutes? neat!
|
||||
Despite that, he is never holding back
|
||||
your blossoming romance with Dr Peat.
|
||||
Don’t deny it, that launch was pretty hard!
|
||||
It’s fifth base next: that’s photos of his feet.
|
||||
It’s fair to say her reputation’s marred.
|
||||
We all regret that we did once anoint
|
||||
her President: her premiership’s ill-starred.
|
||||
Hey - you’re meant to be in charge of this joint!
|
||||
You’re seldom seen cos of the mountaineering
|
||||
meets that you’re always on. You’d made your point
|
||||
before you chose to go off disappearing
|
||||
to New Zealand… we get the message! Plus
|
||||
we’ve had enough of all your domineering:
|
||||
maybe it’s time we put you on a bus!
|
||||
Nah, I’m just joking. All I’ve said’s refutable.
|
||||
But the boys, we mean this next bit, all of us,
|
||||
so stop me Isla if this isn’t suitable
|
||||
but honestly we think your mum is beautiful.
|
||||
|
||||
Alas, I have to bring an end to this rhyme.
|
||||
I know it wasn’t much, in our defence,
|
||||
the fact you used ChatGPT’s a crime.
|
||||
I hope I’ve not caused over much offence
|
||||
don’t worry, that is it, I’ve said my bit,
|
||||
so I’ll turn from the ladies to the gents.
|
||||
Yeah, don’t look away now, we wrote this shit!
|
||||
I see you looking at your laces, Chris!
|
||||
Wit without real goodwill is not legit,
|
||||
so boys, don’t send sincerity to piss!
|
||||
Why did God say he’d take our hearts of stone
|
||||
and give us hearts of flesh? For this, for this!
|
||||
Here is flesh of our flesh, bone of our bone;
|
||||
love, and love nothing more but God alone.
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
# Why Easter is the best week of the year
|
||||
|
||||
Based on a talk given to my colleagues at Scott Logic for Maundy Thursday, 2024.
|
||||
|
||||
Published on: 30 Mar 2024
|
||||
|
||||
As you might have noticed, it is Easter this week! So I'd like to take five or five minutes of your time to share why I – and about two billion other humans going about the place just now – think Easter is the best week of the year. And it's got something to do with a special Christian ritual called Communion.
|
||||
|
||||
Communion, at its heart, is about as simple a ritual as you can get. You get together with a bunch of other people. You share some bread, and you share some wine.
|
||||
|
||||
And it’s because of this ritual that so many people regard Easter as the best week of the year. I want to explain to you why that is, and more than that, I want to convince you that Easter is the best week of the year for you, too!
|
||||
|
||||
If you’ve passed by _The Hub_ at the top of Johnstone Terrace here in Edinburgh recently, you might have notice the banner which is draped over the railings just now – reading, ‘RITUALS THAT UNITE US.’
|
||||
|
||||
Now, that might seem like an odd idea. But wouldn’t that be great, if we actually had a ritual which could unite us? Because the world could surely do with a bit more unity right now. The world seems so divided, and sometimes it seems like there’s no hope for real unity.
|
||||
|
||||
We can see that in our politics. We’re divided about foreign policy, about taxation policy, about trade policy, about environmental policy.
|
||||
|
||||
And the conflicts that we have in this country seem pretty trivial when we remember the conflicts that are playing out in other parts of the world right now. In Israel and Gaza. In Sudan. In Russia and Ukraine.
|
||||
|
||||
And there’s plenty of conflict happening on the small scale, too. Often it’s the smallest-scale conflicts which hurt us the most deeply. Your landlord pushes you around. That friend you trusted like no-one else in the world lets you down. The partner or spouse you loved like no-one else in the world – you end up fighting.
|
||||
|
||||
It’s possible that you’re going to be reading this right now with a heavy heart because of a broken relationship in their life. And doesn’t that hurt more than anything else we know?
|
||||
|
||||
When the world is groaning so heavily under the weight of conflict, and some banner on _The Hub_ tells us a ritual can unite us, that seems so out of proportion to the scale of the problem, doesn’t it? What can a ritual do? A bit of old superstition? An excuse to divide people, maybe – what can a ritual do to unite us?
|
||||
|
||||
Well, two thousand years ago, a man had a meal with his friends. Together, they shared a meal of bread and wine – which, in that time and place, was the most ordinary meal imaginable.
|
||||
|
||||
And yet, in that most ordinary event imaginable, something was happening which was totally unimaginable. As this man, Jesus, shared the elements of this meal, he made some extraordinary statements about what he was doing: ‘take, eat, this is my body’ – ‘drink this, all of you; this is my blood of the new covenant.’ (The word ‘covenant’ means a promise.)
|
||||
|
||||
He told them he wasn’t just giving them bread and wine, he was giving his body and his blood, and a promise.
|
||||
|
||||
Before Jesus ate another meal, he was flogged and nailed to a cross. His blood was spilt and his body broken, even to death.
|
||||
|
||||
And yet, that wasn’t the end of the Easter story. Because three days later, mourners turned up at Jesus’ tomb to pay their respects, and found the tomb empty, the stone rolled away. Then they became the first of crowds of incredulous eyewitnesses to see Jesus, the same Jesus who was killed on a cross, alive.
|
||||
|
||||
Some magic trick, right? But this matters a hell of a lot more than just some magic trick. Because Jesus became the first person in history to prove that you really can both have your cake and eat it. He gave his life, and lived! As a result, we can have his life and our own. We can join with Jesus through the ritual of Communion which he established, and thereby, through Jesus’ body, join together with everyone else who takes part in that ritual, as one body. Then we can start living our brand-new, full-fat, original-recipe life overflowing with generosity where we too can both give our life to others and enjoy it ourselves. Indeed, Jesus taught us and showed us that it’s precisely by giving our lives to others that we get to truly live ourselves.
|
||||
|
||||
This is why, in spite of all the division which persists in the world today, two billion people regard this week as the best week of the year. Two billion people, from every nation on Earth, speaking thousands of languages, of every age and culture and gender and race, who defy the divisions of this world to insist on joining together as one body in Jesus.
|
||||
|
||||
Because Jesus’ new covenant, his promise to all of us, is that in an apparently hopelessly divided world, there exists real hope for unity. And that’s why Easter is the best week of the year.
|
||||
|
||||
@@ -0,0 +1,16 @@
|
||||
# Tracking pixels
|
||||
|
||||
Concerning a notice in the privacy policy of an HR app
|
||||
|
||||
Published on: 10 Apr 2024
|
||||
|
||||
I recently made the mistake of reading the privacy policy of the HR app my employer uses. Take this choice excerpt:
|
||||
|
||||
> *Tracking Pixels*
|
||||
>
|
||||
> We may place tracking pixels in our Applicant Tracking System (ATS). These pixels are used for analytics purposes, including to track statistical information around when an email sent to you is opened.
|
||||
|
||||
Translation:
|
||||
|
||||
> We reserve the right to know whether you have read our emails, how long you spent reading them, at what time and in what physical location you read them, and any other information we can get our hands on. We reserve the right to do this as soon as you open an email, without asking for your permission first, and ask for your forgiveness later. That is, if you ever find out: which you won't, because we also reserve the right to hide this information in a Privacy Policy which we know you won't read, and we design our data-harvesting monster to be completely undetectable to anyone except determined experts, on purpose. We reserve the right to leave this data lying unused in a data warehouse where someone might steal it, and we also reserve the right to use it, if we can think of something satisfactorily dastardly to do with it. On the bright side, we probably won't, so having your data leaked to hackers and fraudsters is probably the worst you have to worry about. Unless we sell your data to advertisers, or a ~black hole of stolen data~ Large Language Model. Oh yeah, we probably reserve the right to do that, too. We doubt anyone will ever check.
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
# Who consecrates the tabernacle? (Ex 29)
|
||||
|
||||
A quick, cursory and possibly completely rubbish observation I've made on Exodus 29.
|
||||
|
||||
Published on: 11 Apr 2024
|
||||
|
||||
I've been reading Exodus recently, and the ending of Chapter 29 stuck out to me.
|
||||
|
||||
For pages and pages (since Chapter 25!) God has been giving Moses exact and exorbitant instructions for how to build the tabernacle, what offerings to give upon it, who the priests are going to be, what the priests are going to be wearing. It's the fanciest IKEA manual you've ever read. No expense spared. Everything is drowning in gold, silver, incense, myrrh, silk, fragrant oil, you name it.
|
||||
|
||||
What's this about? The answer seems obvious: it's to sanctify the temple! To make it beautiful enough and pure enough that even God could live there.
|
||||
|
||||
But right at the end of Chapter 29, in vv 43-44, there's this wonderful twist (NIV, emphasis mine):
|
||||
|
||||
> ... and the place will be consecrated by *my glory*. So *I* will consecrate the tent of meeting and the altar and will consecrate Aaron and his sons to serve me as priests.
|
||||
|
||||
All this work, and at the end of the day, it's *God* who sanctifies his own temple? So why all the fuss? Well, it looks like the final two verses of the chapter give us the answer:
|
||||
|
||||
> Then I will dwell among the Israelites and be their God. They will know that I am the LORD their God, who brought them out of Egypt so that I might dwell among them. I am the LORD their God.
|
||||
|
||||
So on a cursory reading, it looks like God is telling them something extraordinary about the kind of God he is. He is not like the other gods, who demand this kind of worship to appease their pride. Nor is there, unlike the other gods, anything the Israelites could do to make a place habitable for him. That's because there's nothing the Israelites could do to cleanse themselves of their sin: only the 'glory' of God could do that. And indeed, God has no need of worship to puff up his pride, since his glory existed before the world was made, and human beings can do nothing to either add to it or subtract from it.
|
||||
|
||||
Instead of a vain god who seeks tribute, this is a Father God who seeks to 'dwell' (literally to 'camp') among his people. The God who has put into motion a rescue plan to pull the Israelites out of Egypt specifically for this purpose. As it was in the beginning, when God dwelt in the Garden with Adam and Eve. This is his mission. This is what he's like. And he wants his people to know this, so that they can dwell together.
|
||||
|
||||
@@ -0,0 +1,179 @@
|
||||
# God Is Not Great, initial thoughts
|
||||
|
||||
My spark notes on Hitchen's classic 2007 polemic against religion, plus some initial thoughts on how I want to respond to it.
|
||||
|
||||
Published on: 14 Apr 2024
|
||||
|
||||
These are my 'spark notes' on *God Is Not Great*, Christopher Hitchen's classic 2007 polemic against religion in all its forms, and call to adopt secular humanism as its rightful replacement.
|
||||
|
||||
The book can be coherently read as a collection of independent essays. That said, with a few exceptions, each chapter in *God Is Not Great* contributes to one of three main themes, and I think this is a helpful way of summarising the overall movement of the book. The three themes I've identified are as follows:
|
||||
|
||||
1. Religion is evil
|
||||
2. Religion is untrue
|
||||
3. Secular humanism is a better alternative to religion
|
||||
|
||||
As for the exceptions: Chapters 13 and 17 in part contribute to both the first theme and the third, while Chapters 1, 3, 12 and 14 don't fit into these broad themes, and are self-standing.
|
||||
|
||||
## 1. Religion is evil
|
||||
|
||||
### Chp 2
|
||||
|
||||
* Religion is violent, because:
|
||||
* It has to be missionary, because it is insecure in its own beliefs (p17)
|
||||
* It provokes tribalistic conflict, in a similar manner to racism (pp35-36)
|
||||
|
||||
### Chp 4
|
||||
|
||||
* Religion is bad for your health, because:
|
||||
* Faith in medicine is a threat to religion's thrall (p47)
|
||||
* Religious doctrines may contradict sound medical advice
|
||||
* The right to religious freedom may be abused to deflect criticism of unhealthy practices (p50)
|
||||
* Religion has a special relationship with child abuse, and is incapable of accepting open moral criticism of itself for this
|
||||
|
||||
### Chp 13
|
||||
|
||||
* Religion tends towards evil, because it requires fanaticism in order to spread, and fanaticism tends towards evil (p192)
|
||||
|
||||
### Chp 16
|
||||
|
||||
* Religion causes child abuse, because:
|
||||
* Terrifying children with eschatology is child abuse
|
||||
* Religious education is propaganda and should not be inflicted on children who are not yet mature enough to respond to it rationally
|
||||
* Religion consistently mandates cruel genital mutilation of children
|
||||
* Christians and Muslims have spread misinformation about masturbation, which leads to dangerously sexually repressed adult men, which in turn leads to sexual abuse of children by those men (as well as sexual abuse of women)
|
||||
* Child abuse in churches is not a case of a few bad eggs, it is institutional and based on an ideological need to control the minds and sexual organs of children
|
||||
* Religion institutionalised torture in medieval Europe
|
||||
* Religion makes honest and nuanced debate about abortion impossible, because:
|
||||
* Nuanced debate is pushed out by extreme and implausible religious doctrine
|
||||
* Religious people would rather use the unborn as objects of doctrine than human beings in need of protection
|
||||
|
||||
### Chp 17
|
||||
|
||||
* Religion is the only reason anti-Semitism is possible
|
||||
* Religion in its fullest expression is indistinguishable from totalitarianism, because:
|
||||
* The defining characteristic of both religion and totalitarianism is the absolute right to rule of the ruler, even when they rule with caprice
|
||||
* Religion and totalitarianism are also characterised by the need to extinguish heresy with violence
|
||||
* Religion and totalitarianism alike must propose a total solution to all life's problems, require blind faith from its adherents, and demand all aspects of life public and private be submitted to total supervision. This doesn't bring out the best in us
|
||||
* Religious/totalitarian systems are unable to take accountability and therefore improve over time, in contrast to secular humanist systems
|
||||
* History has proven this as fact:
|
||||
* In the ancient world, religious totalitarianism was the normal form of government
|
||||
* Calvin, the inspiration for the Presbyterian Christian tradition, which included South African apartheid, was the epitome of a totalitarian dictator, demanding total control on the private lives of his citizens in Geneva, on the pain of humiliation in this life and eternal torment in the next
|
||||
* History has also proven that, rather than standing in opposition to the supposedly secular totalitarianisms of the twentieth century, religion actually aided and abetted totalitarianism:
|
||||
* Rome supported fascist movements throughout Europe, including Italy, Hungary, Spain, and Ireland
|
||||
* Rome accommodated Naziism by handing over control of its schools, permitting the use of parish records to identify those with Jewish ancestry, disbanding Catholic opposition political parties, declaring Hitler's birthday a Church holiday, and running the 'rat line' to South America after the military defeat of Naziism
|
||||
* Although not quite as arse-licking as the Vatican, Germany's Protestant churches also mostly capitulated to Nazi totalitarianism
|
||||
* Japanese soldiers committed enormous atrocities across the Far East in the name of their god-emperor, Hirohito
|
||||
* The strategy of the Communists was first, to use religion as a prop to gain power, and then to replace religion with itself. Notice the striking commonalities between religion and communist totalitarianism:
|
||||
* Infallible leaders
|
||||
* A permanent war on heresy
|
||||
* Institutionalised torture
|
||||
* Scapegoating the innocent rather than accepting accountability for failures
|
||||
* Justifying any means necessary in order to achieve an ultimate end
|
||||
|
||||
## 2. Religion is untrue
|
||||
|
||||
### Chp 5
|
||||
|
||||
* Religion was a barbaric attempt to explain physical phenomena. Science now does a much better job, so religion can be discarded as a redundant theory
|
||||
|
||||
### Chp 6
|
||||
|
||||
* Religion is 'solipsistic', which is to say:
|
||||
* Religion divides the world into an in-group and an out-group
|
||||
* When the in-group receives good fortune, that is interpreted as God's blessing
|
||||
* When the in-group receives bad fortune, this is inexplicable
|
||||
* Whatever happens to the out-group is irrelevant
|
||||
* This is a redundant theory which explains little, and therefore we should not believe it
|
||||
|
||||
### Chp 7
|
||||
|
||||
* We should believe that the Pentateuch is a fiction, because:
|
||||
* Exodus is inconsistent with the archaeological evidence
|
||||
* Textual evidence in Deuteronomy suggests the texts were written much later than the supposed events were supposed to have taken place
|
||||
* Throughout the Pentateuch, Moses is referred to in the third person, which is not consistent with the claim that Moses himself authored it
|
||||
* The Pentateuch contains events we should *hope* to be false, such as Moses ordering multiple massacres, and the Ten Commandments classifying wives as their husbands' property
|
||||
* The Pentateuch, indeed, the whole Bible, is limited in scope to a small corner of the Middle East, which is not consistent with the universal nature of the supposed God who is supposed to have inspired its authorship
|
||||
|
||||
### Chp 8
|
||||
|
||||
* We should not believe the Gospels, because:
|
||||
* Matthew and Luke disagree on the virgin conception
|
||||
* Matthew and Luke disagree on the genealogy of Jesus
|
||||
* Matthew and Luke disagree on when Mary and Jesus escaped to Egypt
|
||||
* Luke dates the birth of Christ during both the reign of Herod in Judea and the governorship of Quirinius in Syria, but these two events did not overlap, so this is impossible
|
||||
* As far as we know, the Romans did not, and would not, demand that the people assemble in one place in order to be counted for a census
|
||||
* The Gospels disagree about the Sermon on the Mount
|
||||
* The Gospels disagree about the Anointing of Jesus
|
||||
* The Gospels disagree about the Crucifixion and Resurrection of Jesus
|
||||
* The Gospels disagree about the betrayal of Judas
|
||||
* The Gospels disagree about the denial of Peter
|
||||
* John suggests he thinks Jesus was probably born in Galilee to an ordinary family with no proven link to King David's genealogy
|
||||
* Mary's attested behaviour during the ministry of Jesus is not consistent with the Nativity story
|
||||
* John 8:3-11 (the stoning of the woman caught in adultery) is a later insertion to John's Gospel
|
||||
|
||||
### Chp 9
|
||||
|
||||
* The Koran is borrowed from a hotchpotch of Jewish and Christian myths
|
||||
|
||||
### Chp 10
|
||||
|
||||
* Miracles (such as the Resurrection of Jesus) should not be believed, because:
|
||||
* See Hume's *On Miracles*
|
||||
* Extraordinary claims require extraordinary evidence
|
||||
* Believing miracles is comparable to believing reports of aliens (p144)
|
||||
|
||||
### Chp 11
|
||||
|
||||
* Religions are founded in credulity
|
||||
|
||||
### Chp 15
|
||||
|
||||
* The crucifixion story makes no sense, because:
|
||||
* I'm supposed to be morally responsible for Adam's sin, but I amn't!
|
||||
* Even Adam can't be fully blamed for Adam's sin, because he was set up!
|
||||
* The Jews who crucified Jesus are supposed to be blameworthy for their crime, even though the crucifixion was allegedly both necessary and inevitable
|
||||
* I'm allegedly given the free will to either accept or deny the offer, even though denying the offer will lead to an eternity of torment: any sensible God who cared a mite would not have given me the choice
|
||||
* Religious rules are impossible to follow, and this leads to either spiritual policing, organised hypocrisy, or both
|
||||
|
||||
## 3. Secular humanism is a better alternative to religion
|
||||
|
||||
### Chp 13
|
||||
|
||||
* Faith has inspired great heroism. But the heroism is better explained by the heroes' humanism than it is by their faith itself
|
||||
* For example, Martin Luther King Junior didn't really preach Christianity, because he preached forgiveness, while Christ preached eternal torment for the 'inattentive' (pp175-6)
|
||||
|
||||
### Chp 17
|
||||
|
||||
* Religion is the only thing sustaining anti-Semitism
|
||||
* Secular humanist political systems can take accountability, respond to criticism and improve over time, while religious systems exempt themselves from legitimate criticism, stifling progress
|
||||
* The only alternative to totalitarianism is pluralism, which is inherently secular
|
||||
|
||||
### Chp 18
|
||||
|
||||
* Secular humanism has been a powerful positive force throughout history in face of oppression by religion, as proved by example:
|
||||
* Socrates proved that conscience is innate, and that a great way to mock dogma is with satire which pretends to accept that dogma
|
||||
* Lucretius, Democritus and Epicurus had better explanations for the way the world worked than religion (which is why their work was suppressed in Christian Europe and nearly lost forever as a result). Once rediscovered, their ideas kick-started the Scientific Revolution in Europe
|
||||
* Spinoza's deistic ideas had a huge influence despite Jews collaborating with their Christian oppressors to try and ban his writing out of existence
|
||||
* Boyle and Voltaire may have been closet atheists, agnostics or deists
|
||||
* Kant 'overthrew' the cosmological and ontological arguments for the existence of God, and proved (by means of the Categorical Imperative) that human decency does not require any theological assumptions
|
||||
* Let's chuck some more names in the ring: Gibbon, Hume, Paine, Franklin, Darwin, Einstein
|
||||
* Jews were once doubly ghettoed: on the outside by oppressive Christians, and on the inside by oppressive self-racialisation. Secular humanism freed Jews from both these ghettoes, which in turn led to an outpouring of secular Jewish brilliance
|
||||
* Ancient Jews were on the road to a quasi-secular Hellenism, before that was ruined forever by the tyrannical and fanatical Judas Maccabeus, with disastrous consequences for the history of Western civilisation. The Abrahamic religions we know today were not inevitable, and it is possible to imagine what Western history would have been like without it
|
||||
|
||||
### Chp 19
|
||||
|
||||
* Secular humanism is a better alternative to religion, because:
|
||||
* Religion requires clinging to immovable dogma and being unwilling to change your mind
|
||||
* Seeking truth requires being willing to change your mind
|
||||
* Secular humanism is therefore on the side of seeking truth, and religion is on the side of wilful ignorance
|
||||
* Secular humanism is on the side of progress, because it is what enables the expansion of scientific knowledge and the development of new technology
|
||||
|
||||
## The odds and ends
|
||||
|
||||
* Chp 1: an introduction to the themes of the book with little substantial
|
||||
* Chp 3: titled 'A Short Digression on the Pig', it does what it says on the tin
|
||||
* Chp 12: titled 'A Coda: How Religions End', it does what it says on the tin
|
||||
* Chp 14: contrary to the hopes of some Westerners disillusioned with organised Western religion, Eastern religions like Buddhism, Hinduism and Taoism are not a solution to the problems of religion
|
||||
|
||||
I would be interested to try writing apologetic and/or evangelistic responses to these ideas. But it's not a priority for me right now. Anyway, if I ever want to come back to it, I'll probably come back to these spark notes to give me a head start.
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
# How I made YouTube work for me
|
||||
|
||||
I just learned YouTube channels have an RSS feed. This is terrific news.
|
||||
|
||||
Published on: 2 May 2024
|
||||
|
||||
One of my bad habits in life is wandering through YouTube. I've always had AutoPlay turned off, but I still found myself switching off and sleepwalking from one 'recommendation' to the next.
|
||||
|
||||
A lot of what I watch in these times is crap. It's often when I'm tired and just want to switch off, so naturally enough, longer, more emotionally or intellectually material – in other words, exactly the kind of videos I actually *do* want to watch – I ignore. (For me, it's often mediocre sketch comedy videos. That's my poison, it turns out.)
|
||||
|
||||
Now, there is a time for switching off and doing something light. But I don't want watching junk videos to be my answer. Any more than when I'm hungry after a long day of work, I don't want to be resorting to junk food all the time. I really want to get out of this bad habit, and though it's not a huge problem, I've still not been able to fully kick it, either.
|
||||
|
||||
Still, there are YouTube channels I really *want* to keep up with. Musicians. Short film channels. Video essayists. And, yes, even one or two sketch channels: though YouTube is a bit flooded with sketch comedy, some it is really good and brings me joy, and that's a good thing!
|
||||
|
||||
This is where RSS comes in.
|
||||
|
||||
So if you don't know, an RSS file is a file someone puts on their website which tells you, in a standard format, what pages are on their website. It's a pretty old standard in Web terms, and it's very stable. There are a wide range of apps out there, called 'feed readers', which you can use to keep track of RSS feeds, notifying you when something new gets published in your website and putting it in a feed for you to review.
|
||||
|
||||
It turns out YouTube channels have RSS feeds.
|
||||
|
||||
This is terrific news.
|
||||
|
||||
It means I can use my RSS feed reader to subscribe to YouTube channels, instead of YouTube's own subscription system.
|
||||
|
||||
And that means I don't need any of YouTube's personalisation features. I can delete all my search history, all my watch history, and stop them from collecting any more. This means YouTube is now incapable of providing recommendations that I'm actually likely to click on. Which is exactly what I want.
|
||||
|
||||
This is what my YouTube homepage looks like right now:
|
||||
|
||||
=> /images/blog/2024/05/02/beautiful_youtube_homepage.jpg My YouTube homepage with a blank space where the recommendations used to be
|
||||
|
||||
So I can both subscribe to the channels I'm genuinely interested in, and not get sucked into watching junk.
|
||||
|
||||
Awesome!
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
# LLMs do not understand anything
|
||||
|
||||
Save this for the next time someone tells you that LLMs 'understand' things.
|
||||
|
||||
Published on: 13 Jun 2024
|
||||
|
||||
LLMs do not understand what they are talking about. They just don't. It's not how they're built. They have a statistical model of language, not a semantic one. Philosophical puzzles about whether silicon can be conscious *do not arise_, because LLMs are _not even close to the right shape_ for having _anything like* 'understanding'.
|
||||
|
||||
If you don't believe me, there are plenty of examples out there on the Internet, but this is as good as any. It includes Chat GPT 4o explaining in detail why \~\~A → \~A (which is a classical contradiction) is trivially true in classical logic.
|
||||
|
||||
It's even better given that I had explicitly asked it to explain why that sentence implies the trivial logic, not why it is trivially true. And even had the explanation not been complete garbage from beginning to end, it would only have shown that the sentence was *true*, not that it was trivial.
|
||||
|
||||
In other words, the output:
|
||||
|
||||
* Attempts to prove a contradiction (unprompted!)
|
||||
* Confuses the concepts 'truth' and 'triviality'
|
||||
* Is irrelevant to the prompt
|
||||
|
||||
In case you want it handy, I'll put the full conversation down below. The good bit is at the end. The only edits I've made are to replace TeX syntax with Unicode.
|
||||
|
||||
---
|
||||
|
||||
Me:
|
||||
|
||||
> You have the following axioms.
|
||||
>
|
||||
> 1. |- (A -> B) -> A
|
||||
> 2. |- (~B -> ~A) -> (A -> B)
|
||||
> 3. |- (A -> (B -> C)) -> ((A -> B) -> (A -> C))
|
||||
> 4. A -> B, A |- B
|
||||
>
|
||||
> Prove ~~A -> A.
|
||||
|
||||
Chat GPT 4o:
|
||||
|
||||
> To prove ~~ A → A, we will use the given axioms and inference rules. Let's denote the axioms as follows:
|
||||
>
|
||||
> 1. ⊢ (A → B) → A 2. ⊢ (\~ B → \~ A) → (A → B) 3. ⊢ (A → (B → C)) → ((A → B) → (A → C)) 4. If A → B and A, then ⊢ B
|
||||
>
|
||||
> Here is the proof step-by-step:
|
||||
>
|
||||
> 1. *Axiom (2) Instantiation:* From axiom 2, we have:
|
||||
>
|
||||
> ⊢ (\~ A → \~\~ A) → (\~\~ A → A)
|
||||
>
|
||||
> Let B = A and A = \~ A.
|
||||
>
|
||||
> 2. *Intermediate Step:* To use this axiom, we need to show \~ A → \~\~ A.
|
||||
>
|
||||
> 3. *Negation Introduction:* By definition of negation, \~ A → \~\~ A is a tautology, because if A is false, then \~ A is true, and \~\~ A (which is A) must be false, making \~ A → \~\~ A always true.
|
||||
>
|
||||
> 4. *Modus Ponens Application:* Since \~ A → \~\~ A is true, we apply modus ponens (axiom 4) to derive:
|
||||
>
|
||||
> ⊢ \~\~ A → A
|
||||
>
|
||||
> Thus, we have proved \~\~ A → A using the given axioms and inference rules.
|
||||
|
||||
@@ -0,0 +1,110 @@
|
||||
# Doctor Who, Gayness, and the Church
|
||||
|
||||
Series 14 of Doctor Who has a schizophrenic relationship with Christianity. It’s also gay. I think there might be a connection.
|
||||
|
||||
Published on: 8 Jul 2024
|
||||
|
||||
I’ve recently finished the most recent series of Doctor Who, series fourteen (or ‘Season One’ as our new benevolent overlords at Disney+ are styling it.) It’s pretty fun, by the way. I can recommend it for light watching[^1].
|
||||
|
||||
There’s a few discussion points coming out of that series that would be worth dwelling on. But I’ve been particularly thinking about the schizophrenic attitude the series has taken to Christianity, along with how gay this series is: and what these two themes might fit together, to give us something important to say about Jesus Christ, being gay, and the universe.
|
||||
|
||||
## The Doctor’s schizophrenic relationship with Christianity
|
||||
|
||||
First, let’s look at that schizophrenic attitude to Christianity I mentioned.
|
||||
|
||||
The series ticks up an impressive tally of explicit or strongly implicit references to Christian beliefs and morals, and *none* of them are positive.
|
||||
|
||||
In episode 3, *Boom*, the far-future Anglican church has become an army, with the ranks of the clergy becoming equivalent to arms-bearing ranks in the soldiery. The Doctor claims that ‘the Church’ has been an army for most of its history[^2], and that his companion Ruby Sunday (and therefore us) has been living in a ‘blip’. An all-powerful arms company has tricked the Church into fighting a non-existent foe in order to keep them buying weapons. The Doctor attributes their ability to fall for such a deception to religious faith:
|
||||
|
||||
> I mean, most armies would notice that they were fighting smoke and shadows, > but not this lot, Ruby, you know why? They have faith. Faith! The magic word > that keeps you never having to think for yourself.
|
||||
|
||||
In episode 4, *73 Yards*, Kate Lethbridge-Stewart, head of UNIT, makes this offhand comment, suggesting the oft-repeated claim that all religion is founded in credulity[^3]:
|
||||
|
||||
> That’s what we do, all of us. We see something inexplicable, and invent the > rules to make it work. Mankind saw the sun rise and created God: or we saw the > arrival of a Sontaran, one or the other.
|
||||
|
||||
In episode 5, *Dot and Bubble*, The Doctor is rejected by the people he is trying to save. They rant that he is ‘not one of us’, call his claims about the TARDIS ‘magic’ and ‘voodoo’, and in the same breath assert that it is their ‘God-given duty to maintain the standards of Finetime’ (their space colony).
|
||||
|
||||
In episode 6, *Rogue_, a party of murderous aliens turns up at an upper-class Georgian dance party and demand to be married. The priest denies them, not on the grounds that they are unrepentant murderers with obviously no intention of taking their marriage vows seriously, but on the grounds that they are ‘creatures from hell’, _ie* ‘you don’t look like us’[^4].
|
||||
|
||||
There are other references to Christianity here and there which are, in themselves, neutral or ambiguous. This adds to the sense that Christianity is an important theme for the series.
|
||||
|
||||
But the message is clear. It’s consistently drilled in: Christian beliefs and morals are stupid and bigoted.
|
||||
|
||||
And yet, when the series culminates in its epic two-part finale, the story is plastered wall-to-wall with Christ-like imagery. It transpires that the Doctor has unwittingly been acting as an ‘Angel of Death’ by carrying the invisible God of Death, Sutekh, on his TARDIS, infecting everyone he goes near with the curse of death. Finally, through one of his children, the curse is unleashed, and everyone in the universe is given over to death. Even in death, they continue to suffer, and one of the characters describes themselves as being in ‘hell’. The Doctor battles Sutekh face-to-face and defeats him. Sutekh becomes one of the only creatures which The Doctor, usually a staunch pacifist, can bring himself to kill. Then, the whole world is restored to life. Ruby Sunday even gets to meet her birth mother for the first time, and their relationship is wonderfully restored.
|
||||
|
||||
So on the one hand, any outward sign of Christianity is despised, but the heart of the Christian story — the Resurrection — becomes the template for the climactic redemption story which ties the whole series together.
|
||||
|
||||
That’s what I mean when I say this series has a ‘schizophrenic’ relationship to Christianity.
|
||||
|
||||
## What’s this got to do with gayness?
|
||||
|
||||
In series fourteen, Doctor Who goes gay.
|
||||
|
||||
I’m not playing culture wars here. The Doctor literally kisses a man in episode six.
|
||||
|
||||
=> /images/blog/2024/06/30/ncuti-gatwa-promo-pic.webp Look at this official BBC promo pic and tell me Ncuti Gatwa isn’t playing The Doctor gay.
|
||||
|
||||
But it’s not just that. When we first meet his companion, Ruby Sunday (in the Christmas special), she’s busy falling in love with a woman. Ncuti Gatwa plays The Doctor camp (brilliantly by the way). The Doctor refers to Ruby as ‘babes’. It’s got ‘gay’ written all over it, and this is definitely on purpose.
|
||||
|
||||
From this perspective, it’s not hard to imagine where the hostility to the Church might come from.
|
||||
|
||||
The Church has failed to teach well and Biblically on sexuality, at least in the last couple of centuries. Everyone has suffered as a result of this, but gay people often feel the sharpness of this particularly keenly[^5].
|
||||
|
||||
The Church has put its weight behind a variety of unhelpful teachings on sexuality over the centuries[^6]. But two, contradictory, ones stand out as particularly salient today.
|
||||
|
||||
One is *prudishness*. Sex is evil. Sex is the origin of all evil: the Devil seduced Eve, and Eve seduced Adam, and that’s when it all went downhill. Sex is naughty. Sex is bad. Remember when Jesus said, ‘whoever looks at a woman to lust for her has already committed adultery with her in his heart’ (Matt 5:28)? He was saying that *all sexual desire* is sinful. Remember when Paul advised, ‘It is good for a man not to touch a woman’ (1 Cor 7:1)? He was saying that it’s *bad* for a man to touch a woman *under any circumstances*.
|
||||
|
||||
This is, of course, false and dreadful teaching. The truth is that sex is a gift from God, given so that we can bear his image by loving each other in this most intimate and wonderful way. This is the consistent message of both Testaments. But the idea that there’s somehow something *inherently wrong* with sex has undeniably been a part of the Church’s teaching since at least the Victorian period (and possibly a great deal longer than that).
|
||||
|
||||
The other is that sex is an *essential aspect of humanity*. If you aren’t having sex, you’re missing out on an irreplacable part of your created purpose. This has reacted explosively with the ideas of the Sexual Revolution. The net result is that we have not so much been *freed to have sex* as we’ve been *enslaved to have sex*. Virginity is an embarassment – both for men and for women.
|
||||
|
||||
The radical Biblical idea that you can have a completely fulfilled life, deeply enriched by loving relationships, *without* having sex or getting married, is forgotten.
|
||||
|
||||
Everyone has been harmed by these teachings. But those who experience significant attraction towards the same sex have been harmed double.
|
||||
|
||||
Faced by the impossible demands of bad Church teaching on sexuality on top of the complexities of living with same-sex desire has left those people with nowhere to go. They can *just say ‘no’*, and be made to feel that they’re missing out on completing their full humanity. Or they can indulge their same-sex attraction, and be judged not only promiscuous but a pervert to boot.
|
||||
|
||||
No wonder so many gay people have given up on the Church (and I haven’t even talked about discrimination or violence towards gay people).
|
||||
|
||||
And no wonder that The Doctor has become strikingly anti-Christian at the same time as it has become strikingly gay.
|
||||
|
||||
## What next?
|
||||
|
||||
Doctor Who’s criticisms of the Church hurt when they hit the mark. They hurt more when they’re unfair. But that’s not the point. That point is this: the Church has lost control of the conversation. And we’ve lost control of the conversation because we threw it away. We threw it away encased in bomb-proof concrete and left it to sink to the bottom of the deepest available ocean trench.
|
||||
|
||||
If we in the Church are feeling hurt, we should start by feeling hurt by our own sin.
|
||||
|
||||
The work of regaining trust on the question of sexuality will be the work of decades: and that’s if we start working full-pelt right now. But there is hope.
|
||||
|
||||
I was encouraged last December by the visit to my local church, Bruntsfield Evangelical, of *Living Out*[^7], a charity dedicated to helping churches across the UK talk about sexuality. Ed and Andy, both same-sex attracted men, led us through talks and discussions, and played recordings of perspectives from their same-sex attracted female colleagues who couldn’t make it on the day.
|
||||
|
||||
They were primarily there to talk to us about how to support people like them: same-sex attracted Christians who might be in our church who believe they are called to singleness, helping them to thrive, living their true selves openly, surrounded by love and empowered to share their love with others, just as we want for everyone in our church. In fact, I heard some of the best news I’d ever heard about my own sexuality, even though I am in the minority of people who have never experienced significant same-sex attraction.
|
||||
|
||||
Whether or not you agree with their stance that the right place for sex is within a marriage between a man and a woman, charities like *Living Out* are driving the Church in the right direction: serious, Biblical sexual doctrine which helps us to realise in practice how we are all made in the image of the God of love.
|
||||
|
||||
And how needed! How desperately needed! And Doctor Who gives us a little glimpse of that, too.
|
||||
|
||||
Because not only is the series apparently anti-Christian, it also expresses a need for Christian salvation. The Resurrection story is one which everyone needs to hear, to have their death transformed to life, to have their full humanity affirmed and celebrated and tended and to delight in it and to see it flourish. To know the God of love and life, behind all and over all, with a plan and a means to defeat the grip of death on the world.
|
||||
|
||||
So let’s keep having those frank conversations about sexuality in the Church. It matters for all of us.
|
||||
|
||||
1: Unless you’re bothered by plotholes big enough to fly a TARDIS through. Oh, and you can probably skip episodes 1 and 3.
|
||||
|
||||
=> https://www.doctorwhotv.co.uk/doctor-who-opinion-empire-death-2-102716.htm
|
||||
|
||||
2: For the record, this is flatly false. Though exceptions are widespread, the overwhelming mainstream opinion is that priests should not bear arms. This is not new, but has been the consistent orthodoxy, taken straight from Jesus’ teachings by the Church Fathers and maintained constantly since then. Can the Church be legitimately criticised for its use of violence? Absolutely, let’s have that discussion. Has the Church almost always been a *literal army*? No. The Church has *never* been an army.
|
||||
|
||||
3: See *God is Not Great* by Christopher Hitchens, Chapter 11 for an epitome example of this put forward by a prominent atheist apologist.
|
||||
|
||||
4: In the spirit of charity, I have to accept that this admits of multiple interpretations. It is possible that by calling them ‘creatures from hell’, the priest is referring precisely to their unrepentant murderousness. However, the priest has already tried to avoid the creature’s gaze by the pitiably schoolboyish ploy of *looking elsewhere*, priming the viewers to think that the priest is a silly coward: certainly not the kind to make a noble, principled defence of justice with his head in the jaws of death. Plus, if we interpret ‘creatures from hell’ as meaning ‘you don’t look like us so you must be evil’, that would fit with the consistent framing of the series: that religious morality is equivalent to bigotry.
|
||||
|
||||
5: Though it must be remembered that many gay people have remained and thrived within the Church in spite of the challenges, serving in diverse ways, not least the priesthood.
|
||||
|
||||
6: I found the Ezra Institute to give a good introduction to the history of Church teachings on sexuality.
|
||||
|
||||
=> https://www.ezrainstitute.com/resource-library/articles/sex-and-the-history-of-christianity
|
||||
|
||||
7: For a great and humane introduction to what these guys are like, have a listen to this Living Out podcast episode. I get that if you haven’t grappled with issues like these before, it can be really challenging, and you might find it hard to trust people who take a different view to yourself. I know: I’ve been there myself! The best way to start is to listen to a human voice.
|
||||
|
||||
=> https://www.livingout.org/resources/podcasts/68/misstep-7-godliness-is-heterosexuality-the-plausibility-problem-7
|
||||
|
||||
@@ -0,0 +1,547 @@
|
||||
# What do academics think LLM ‘hallucination’ means?
|
||||
|
||||
What does the word ‘hallucination’ actually mean in reference to LLMs when used by academics? And where does that word come from? I’ve trawled the academic literature for answers.
|
||||
|
||||
Published on: 16 Jul 2024
|
||||
Updated on: 17 Jul 2024
|
||||
|
||||
The word, ‘hallucination’ as applied to LLMs has me enthralled right now. It’s such a *weird* word. And problematic, I think.
|
||||
|
||||
If you don’t know what I’m on about, have a quick look at IBM’s introduction to the topic. It gives you a good intuition what people are talking about, and helpfully illustrates the deep conceptual confusions which have me gripped.
|
||||
|
||||
=> https://www.ibm.com/topics/ai-hallucinations
|
||||
|
||||
But this got me asking: what do people actually mean when they say that an LLM is ‘hallucinating’? And why that word? Where does it come from, and how did it end up in our mouths?
|
||||
|
||||
As far as I could see, nobody seems to have answered this question before, except with the odd bit of unsubstantiated guessing. I think it’s important that we know where this word came from and what it means.
|
||||
|
||||
So I ended up going on a bit of a treasure hunt. I’ve skimmed well over a hundred academic articles to trace where the word came from, how it’s been used over time, and how it’s spread from field to field.
|
||||
|
||||
The result is that I have what I hope is a pretty compelling story of where this weird old word come from and what it’s supposed to mean. I’ve also got an excruciating amount of evidence.
|
||||
|
||||
What I’ll do, is first present my story, and then step through the excruciating detail, providing you with all my sources, so you can check my working, and perhaps see what important evidence I might have missed. If you’re just here for the headlines, you don’t have to read the excruciating bits.
|
||||
|
||||
Before I proceed, two caveats.
|
||||
|
||||
1. I am not a subject matter expert. Judge the quality of my arguments and my evidence. Do not treat me as an authority.
|
||||
2. For the purposes of this post, I’m just considering academic literature. The ways that people use the word ‘hallucination’ in popular discourse may be quite different. (For the record, I think they do: but that’s a story for another day.)
|
||||
|
||||
## The long and short of it
|
||||
|
||||
So this is my theory.
|
||||
|
||||
In 1999, the word ‘hallucination’ was coined accidentally and off-hand by a couple of researchers, Baker and Kanade, in the field of computer vision (CV).
|
||||
|
||||
The word caught on in CV, and came to have a fairly unambiguous meaning. Given an image with missing pixels you want to fill in, ‘hallucinating’ meant generating those missing pixels by means of information in a deep learning model’s training data, rather than by means of any information contained in the input image. (This was also known as ‘example-based in-painting’). It was a term of art, not jargon.
|
||||
|
||||
Then, sometime between 2017 and the end of 2018, a few different researchers in natural language processing (NLP) adopted the term. They were probably aware of the term's usage in CV, and transferred it to mean something similar in NLP.
|
||||
|
||||
When these NLP researchers used it, they used it to refer to when a model produces content which is irrelevant to the input, or contains information not contained in the input.
|
||||
|
||||
When the word ‘hallucination’ first appeared in two or three papers in NLP, the authors used it as a technical term for their own limited purposes. However, it was soon adopted in various contexts for similar concepts.
|
||||
|
||||
For example, in image captioning, ‘hallucination’ came to mean producing a caption which mentions an object which wasn’t depicted in the input image. In machine translation, it came to mean generating a translation which was in the right language, but which meant something completely irrelevant to the input. In abstractive summarisation, it came to mean producing a summary containing details which weren’t in the text the model was supposed to summarise.
|
||||
|
||||
When the term entered NLP, it underwent a striking transformation. It acquired a *valence*.
|
||||
|
||||
In CV, the term referred to normal behaviour, and was value-neutral. It was just a description of what a certain machine does. ‘We need to fill in these missing pixels. The model will do that by hallucinating them.’
|
||||
|
||||
In contrast, in NLP, the term ‘hallucination’ was always used to describe *abnormal* behaviour, and almost always used with a negative valency. In other words, while CV folk used it to describe what they expected their models to do, NLP folk used it to describe a *bug*.
|
||||
|
||||
(There were odd exceptions, though. You do get the periodic paper which insists that there are positive applications of hallucination. But the fact they have to insist so hard rather proves that that boat has already sailed. And even they are still buying in to the idea that hallucination is abnormal behaviour.)
|
||||
|
||||
Now, that brings us up to about 2020. From 2020, we get another change.
|
||||
|
||||
From about 2020 until the present, academics have attempted to *jargonise* the word ‘hallucination’. Broadly, they have so far *failed*.
|
||||
|
||||
When I say that people have attempted to ‘jargonise’ the word, I mean that people are using it while assuming a specific definition. They are using it with technical qualifiers like ‘extrinsic’. They are using it without explaining the meaning or the context, as if you should already know what the word means. And ‘hallucination’ itself is becoming an object of study.
|
||||
|
||||
When I say that they have ‘failed’, I mean that there is no widely agreed and specific meaning for the word, which in my mind, is a crucial feature of jargon. However, the intended meanings tend to coalesce around the idea of an abnormal behaviour of LLMs whereby they produce output which is not epistemically supported by their input.
|
||||
|
||||
## Excruciata
|
||||
|
||||
OK, that was the long and short of it. Now for the excruciating detail. To recap, I think these six claims are enough to support my theory:
|
||||
|
||||
1. Since 2022, academics have treated ‘hallucination’ as jargon
|
||||
2. Since 2017/18, the word ‘hallucination’ has typically been used to describe LLMs producing unfaithful output
|
||||
3. Up to now, academics have not agreed a specific meaning for the word ‘hallucination’
|
||||
4. The word ‘hallucination’ entered the NLP literature around 2017/2018, probably from CV
|
||||
5. The word ‘hallucination’ was not jargon in CV, but was a term of art for example-based in-painting
|
||||
6. The word ‘hallucination’ entered the CV literature in Baker & Kanade 1999
|
||||
|
||||
I’ll work through each of these in turn, showing how I got there from the available evidence.
|
||||
|
||||
Feel free to use this as a cheap way to harvest citations for your own research.
|
||||
|
||||
### 1. Since 2022, academics have treated ‘hallucination’ as jargon
|
||||
|
||||
My evidence for this is twofold: surveys of ‘hallucination’ usually treat the word as jargon, and many original research papers do, too.
|
||||
|
||||
First, let’s look at those surveys. These first five all belong together.
|
||||
|
||||
- Ji et al 2022 [^16] - Liu et al 2023 [^30] - Rawte et al 2023 [^42] - Wang, Cunxiang et al 2023 [^48] - Huang, Lei et al 2023 [^13]
|
||||
|
||||
All the latter four of these surveys lean heavily on Ji et al 2022 for their definition of ‘hallucination’. Since they all source their definition of ‘hallucination’ from Ji et al 2022, it follows that their definitions are all extremely similar, and often verbatim. Ji et al 2022 had this to say about the word ‘hallucination’:
|
||||
|
||||
> Within the context of NLP, the most inclusive and standard definition of > hallucination is the \[sic\] generation that is nonsensical or unfaithful to > the provided source content.
|
||||
|
||||
They also made a distinction between *intrinsic* hallucination, which they regarded as ‘the generation output that contradicts the source content’, and *extrinsic* hallucination, which they regarded as ‘the generation output that cannot be verify \[sic\] with the source content’. Some of the other surveys pick up on this intrinsic/extrinsic distinction. To me, extending the word with technical epithets suggests they regard the word itself as already having an agreed, specific meaning.
|
||||
|
||||
Meanwhile, Li, Wei et al 2022 [^26], another survey, offers no definition of ‘hallucination’, but uses it freely along with the intrinsic/extrinsic distinction. This suggests they expect their expert readers to already know some agreed meaning of the word ‘hallucination’. This is a hallmark of jargon in my books.
|
||||
|
||||
Original research also shows the word ‘hallucination’ being used as jargon. For example, Maynez et al 2020 [^35], despite being often cited when other authors first introduce the term ‘hallucination’, provides no definition of the term. They do, however, use the intrinsic/extrinsic distinction (this might be the paper which coined the distinction).
|
||||
|
||||
All the following papers use the word ‘hallucination’, sometimes in passing comments, sometimes as the principal focus of the paper, without attempting to define the word.
|
||||
|
||||
- Mao et al 2020 [^32] - Wang, Alex et al 2020 [^47] - Lin et al 2022 [^29] - Kumar et al 2022 [^21] - Lee, Hwanhee et al 2022 [^23] - Li, Junyi et al 2023 [^27] - Guerreiro et al 2023 [^12] - Dahl et al 2024 [^6] - Song et al 2024 [^46]
|
||||
|
||||
Dahl et al 2024 also use the word without defining it, even as they tack on their own bespoke technical epithets, ‘open-domain’ and ‘closed-domain’. Plus, in many of these examples, the context is not enough to make clear what the word ‘hallucination’ is taken to mean.
|
||||
|
||||
All these examples demonstrate that the authors assume that their audience, *viz* technical experts, will come with an agreed and specific meaning of the word ‘hallucination’ pre-baked and ready for precise academic application.
|
||||
|
||||
In other words, these authors, including both surveys and primary literature, use the word ‘hallucination’ as if it is jargon.
|
||||
|
||||
### 2. Since 2017/18, the word ‘hallucination’ has typically been used to describe LLMs producing unfaithful output
|
||||
|
||||
Recall those surveys I referred to before. They mostly depended on Ji et al 2022’s definition, which was:
|
||||
|
||||
> \[...\] generation that is nonsensical or unfaithful to the provided source > content. [^16]
|
||||
|
||||
Whatever we might think about ‘hallucination’, the word ‘unfaithful’ really is a jargon word in the field of natural language processing, with an agreed, specific meaning. An LLM is ‘unfaithful’ just in case it produces output which is not epistemically supported by the input.
|
||||
|
||||
This is most often used in the case of summarisers. In that case, a summariser is unfaithful just in case it produces a summary containing information which is not implied by any information in the document it was supposed to summarise.
|
||||
|
||||
(‘Nonsensical’ is not a jargon term as far as I know. I have never encountered any attempt in the NLP literature to define ‘nonsensical’, and although this definition is often quoted, the term ‘nonsensical’ is rarely used in practice.)
|
||||
|
||||
Now, I am not claiming that this is the only way or even the dominant way in which the term ‘hallucination’ has been used. Indeed, in section 3, I’m going to show precisely that this is *not* the case: in fact, the word ‘hallucination’ continues to be used in diverse ways in the academic literature.
|
||||
|
||||
All I want to claim here is that it is *typical* for academics to use the word ‘hallucination’ to mean something in the rough area of unfaithfulness.
|
||||
|
||||
This is an important part of the story, because this is the meaning which links the word most closely to its etymological roots in computer vision.
|
||||
|
||||
All I need to do really is provide enough citations. I know I haven’t read everything. But if what was typical in my reading is unusual in the literature at large, I’ve been the victim of some extraordinary bad luck. Have a look at these papers:
|
||||
|
||||
* Durmus et al 2020 [^7] defines ‘hallucination’ as one of two kinds of failures of faithfulness
|
||||
* Huang, Luyang et al 2020 [^14] defines ‘hallucination’ as ‘creating content not present in the input’
|
||||
* Maynez et al 2020 [^35] introduces ‘hallucination’ as a cause of unfaithfulness
|
||||
* Zhao et al 2020 [^56] defines ‘hallucination’ as ‘including material that is not supported by the original text’
|
||||
* Nan et al 2021 [^38] defines ‘hallucination’ as putting out claims not supported by the input
|
||||
* Zhou, Chunting et al 2021 [^59] defines ‘hallucination’ as failures of faithfulness in machine translation
|
||||
* Mao et al 2020 [^32] clearly uses ‘hallucination’ to mean unfaithfulness
|
||||
* King et al 2022 [^18] is aware of usages of ‘hallucination’ to refer to unfactuality, but narrows in on failures of faithfulness, which they call ‘consistency’
|
||||
|
||||
So there you have it. ‘Hallucination’ has widely been taken to roughly mean ‘unfaithfulness’.
|
||||
|
||||
### 3. Up to now, academics have not agreed a specific meaning for the word ‘hallucination’
|
||||
|
||||
So we know that it was normal for academics to use ‘hallucination’ to mean something like ‘unfaithfulness’. But was it also normal for academics to use it for other meanings?
|
||||
|
||||
I think it was. There are a number of ways which authors used the word which are not consistent with the ‘unfaithfulness’ interpretation.
|
||||
|
||||
The main way is that authors have assumed that in order to be a ‘hallucination’, the output has to *contradict* something: either the input, or the training data, or the facts, or itself. This contrasts with the ‘faithfulness’ interpretation, under which a hallucination can be perfectly consistent with the input, the training data, the facts, and itself, as long as it isn’t *supported* by the input.
|
||||
|
||||
All the following papers are clear that hallucination requires contradicting something, usually the facts:
|
||||
|
||||
* Huang, Yichong et al 2021 [^15]
|
||||
* Zhu et al 2021 [^60]
|
||||
* Pagnoni et al 2021 [^40]
|
||||
* Shuster et al 2021 [^45]
|
||||
* Zhang, Yue et al 2023 [^55]
|
||||
* Rawte et al 2023 [^42]
|
||||
* Dahl et al 2024 [^6]
|
||||
* Magesh et al 2024 [^31]
|
||||
|
||||
On the other end of the spectrum, a few authors seemed to believe that hallucinated outputs *cannot* contradict the corresponding inputs. (This is also inconsistent with the ‘unfaithfulness’ view.)
|
||||
|
||||
* Durmus et al 2020 [^7]
|
||||
* Huang, Luyang et al 2020 [^14]
|
||||
* Nan et al 2021 [^38]
|
||||
|
||||
There’s also disagreement on whether ‘nonsense’, or ‘incoherence’, counts as hallucination.
|
||||
|
||||
On the one hand, Durmus et al 2020 [^7] argue that nonsensical outputs are not hallucinations, since it doesn’t make sense to ask whether nonsensical outputs are faithful. Likewise, Shuster et al 2021 [^45] contrast hallucination with incoherence.
|
||||
|
||||
But on the other hand, Pagnoni et al 2021 [^40] include misleading and incorrect grammar in their definition of ‘hallucination’, while Ji et al 2022 [^16] explicitly include ‘nonsensical’ outputs in their widely-quoted definition of ‘hallucination’.
|
||||
|
||||
Some authors have managed to recognise the ambiguity of the term. Both King et al 2022 [^18] and Farquhar et al 2024 [^9] acknowledge that the word ‘hallucination’ has been used variably to cover failures of faithfulness and failures of factuality, and are careful to define their terms for their own purposes to avoid being misunderstood in the context of this ambiguity.
|
||||
|
||||
So it seems that although many academics have treated the term ‘hallucination’ as jargon, in actual fact, there is no widely agreed specific meaning of the word.
|
||||
|
||||
<hr>
|
||||
|
||||
I will slide in here with a quick side note. While some authors treated ‘hallucination’ as jargon for unfaithfulness or unfactuality, other authors contemporaneously managed to talk about these topics without using the word ‘hallucination’ at all. Here are some examples:
|
||||
|
||||
* Cao, Ziqiang et al 2018 [^3]
|
||||
* Li, Haoran et al 2018 [^25]
|
||||
* Falke et al 2019 [^8]
|
||||
* Goodrich et al 2019 [^11]
|
||||
* Kryściński et al 2019 [^20]
|
||||
* Cao, Meng et al 2020 [^4]
|
||||
* Zhang, Yuhao et al 2019 [^54]
|
||||
* Marcus & Davis 2020 [^33]
|
||||
* Marcus 2020 [^34]
|
||||
* Krishna et al 2021 [^19]
|
||||
* Bai et al 2022 [^1]
|
||||
* Weidinger et al 2022 [^50]
|
||||
* Perez et al 2022 [^41]
|
||||
* Min et al 2023 [^36]
|
||||
* Muhlgay et al 2024 [^37]
|
||||
|
||||
Probably not a significant enough point to merit a whole section. But there you are. I think it adds to the picture that ‘hallucination’ is failed jargon.
|
||||
|
||||
### 4. The word ‘hallucination’ entered the NLP literature around 2017/2018, probably from CV
|
||||
|
||||
So people have been using the word ‘hallucination’ in the NLP literature recently. But where did it come from?
|
||||
|
||||
I think it entered the NLP literature somewhere around 2017/18, and probably was borrowed from the field of computer vision (CV).
|
||||
|
||||
I can't offer a theory for a single, original usage of the word in NLP. But there are three papers I feel are pretty close. These are the three oldest papers I could find in the NLP literature which use the word ‘hallucination’.
|
||||
|
||||
* Wiseman et al 2017 [^51]
|
||||
* Rohrbach et al 2018 [^44]
|
||||
* Lee, Katherine et al 2018 [^22]
|
||||
|
||||
Both Rohrbach et al and Lee et al use a form of language which suggests they are intentionally coining a technical term. Here’s Rohrbach et al:
|
||||
|
||||
> In Figure 1 we show an example where a competitive captioning model, Neural > Baby Talk (NBT) (Lu et al., 2018), incorrectly generates the object “bench.” > We refer to this issue as object *hallucination*.
|
||||
|
||||
And here’s Lee et al:
|
||||
|
||||
> These mistranslations are completely semantically incorrect and also > grammatically viable. They are untethered from the input so we name them > *‘hallucinations’*.
|
||||
|
||||
I have no reason to believe that these two papers are deliberately plagiarising each other. It’s reasonable to assume that these two papers genuinely coined a similar term for a similar phenomenon at the same time.
|
||||
|
||||
Wiseman et al 2017, in contrast, doesn’t look like it’s attempting to coin a technical term. They just use the word once, presumably as a stylistic flourish to help illustrate their point. But they do use it for a closely related concept.
|
||||
|
||||
> \[…\] we see the model hallucinates factual statements, such as “in front of > their home crowd,” which is presumably likely according to the language model, > but ultimately incorrect (and not supported by anything in the box- or line- > scores).
|
||||
|
||||
Just to add to the picture, Ehud Reiter, in his 2018 blog post [^43], gives us an insight into the International Natural Language Generation conference of 2018. He claims that at that conference, ‘hallucination’ was a hot topic of discussion, and cites Rohrbach 2018 to support his claim that ‘hallucination is a well-known problem in neural approaches to image captioning’.
|
||||
|
||||
It might be fruitful to have a peruse of the [INLG 2018 Proceedings](https://aclanthology.org/events/inlg-2018) to see whether that interest in ‘hallucination’ was reflected in the written contributions, or if it was mainly contained in verbal discussions. I haven’t taken the liberty to do this myself: by all means, have a look yourself and let me know what you find!
|
||||
|
||||
I think all this suggests that the word ‘hallucination’ entered the field gradually, not with a bang, and perhaps spread by word of mouth at conferences as much as it spread through published papers, at least at first.
|
||||
|
||||
But we still have to explain why all these different authors seem to have independently come up with a similar meaning for the word ‘hallucination’.
|
||||
|
||||
I think the best explanation is that they got the word ‘hallucination’ from computer vision (CV). If my fifth section is cogent, then ‘hallucination’ was used in CV to refer to deep learning models generating data based on information in their training data, not from information contained in or implied by the input. This would explain how independent authors in NLP all independently coined the word ‘hallucination’ in their own field to mean pretty similar things. They were probably aware of the usage in the CV literature and adopted it by analogy.
|
||||
|
||||
So, I reckon the word ‘hallucination’ probably entered the NLP literature from a few authors independently, and they chose that word because they were borrowing it from the CV literature, where it was already being used for a similar concept.
|
||||
|
||||
But that depends on my next claim: so let’s look at that!
|
||||
|
||||
### 5. The word ‘hallucination’ was not jargon in CV, but was a term of art for example-based in-painting
|
||||
|
||||
I want to argue that ‘hallucination’, although it wasn’t jargon, was widely used in the computer vision (CV) literature to refer to what was more technically called ‘example-based in-painting’, that is, filling in gaps in images using the information from training data baked into neural networks.
|
||||
|
||||
First look at Baker & Kanade 1999 [^2]. If my sixth section is correct, this is where the term entered CV, but that’s not crucial to my argument here. Even if I’ve missed some crucial evidence, it is nonetheless pretty certain that they had a seminal effect on the use of the word in the field – they are early in the field’s history, and widely cited by other CV papers which use the word ‘hallucination’. They’re even cited as the origin of the term in machine learning by the NLP paper, Farquhar et al 2024 [^9], a quarter of a century later.
|
||||
|
||||
Baker & Kanade are writing about a new algorithm they’ve used in order to increase the resolution of low-resolution images of human faces. The intended application is for surveillance camera footage. They use the word ‘hallucination’ once in their title (‘Hallucinating faces’), once in their abstract, and 79 times in the main body of the text.
|
||||
|
||||
Across those 79 occurrences, they are using it to refer to one of three things:
|
||||
|
||||
* Their algorithm: *eg_ their ‘face hallucination algorithm’
|
||||
* The output of their algorithm: _eg_ ‘hallucinated faces’
|
||||
* What their activity does: _eg* ‘a face is hallucinated by our algorithm’
|
||||
|
||||
The closest they come to explaining what they *mean* by the word is in their abstract:
|
||||
|
||||
> Although numerous resolution enhancement algorithms have been proposed in the > literature, most of them are limited by the fact that they make weak, if any, > assumptions about the scene. We propose an algorithm that can be used to learn > a prior on the spatial distribution of the image gradient for frontal images > of faces. We proceed to show how such a prior can be incorporated into a > super-resolution algorithm to yield 4-8 fold improvements in resolution (16-64 > times as many pixels) using as few as 2-3 images. The additional pixels are, > in effect, hallucinated.
|
||||
|
||||
(By ‘super-resolution’, they mean increasing the resolution of images. This is typically reduced to a particular kind of ‘image in-painting’ problem, which in general means filling in gaps in images.)
|
||||
|
||||
So, their idea is that, rather than limiting your algorithm to the information contained in the input image, you can get better results by baking in assumptions about the image to the algorithm.
|
||||
|
||||
Why is this supposed to work? They hope that for a clever enough algorithm, the information that ‘this blurry splodge is a full-frontal portrait of a human face’ will provide just enough information to accurately guess what a higher-resolution version of the image would have been.
|
||||
|
||||
As for how that information, about what full-frontal portraits of human faces look like, gets baked into the algorithm in practice: that’s done by training a neural network on full-frontal images of faces. Hence why this field was so close to NLP, which, in recent years at least, has leaned heavily on neural networking or ‘deep learning’ approaches.
|
||||
|
||||
To recap, they don’t provide a specific meaning, but they do use it to roughly mean the process of inventing missing pixels in images, not on the basis of information contained in the input, but based on information contained in training data instead.
|
||||
|
||||
To see how this term was picked up by later authors in the field working on super-resolution, in-painting and other related tasks, see:
|
||||
|
||||
* Criminisi 2004 [^5]
|
||||
* Fawzi et al 2016 [^61]
|
||||
* Nazeri et al 2019 [^39]
|
||||
* Xiong et al 2019 [^53]
|
||||
* Xiang et al 2022 [^52]
|
||||
|
||||
But also notice other papers, on similar topics, which get on just fine without using the term at all:
|
||||
|
||||
* Karras et al 2017 [^17]
|
||||
* Zhou, Bolei et al 2017 [^58]
|
||||
* Liao et al 2018 [^28]
|
||||
|
||||
And notice how Wang, Zhihao et al 2020 [^49] introduce the word, as an alternative to another technical term:
|
||||
|
||||
> Face image super-resolution, a.k.a. face hallucination (FH), can often help > other face-related tasks
|
||||
|
||||
The fact that nobody ever attempts to define the word ‘hallucination’, and it doesn’t appear to be required lingo in any field, no matter how niche, to me implies that it wasn’t treated as jargon in CV, at least during the period from 1999 until 2018ish. (The usage in reference to LLMs may well have gone back to affect the usage in CV: I haven’t checked.)
|
||||
|
||||
So again. The word ‘hallucination’ was used in CV roughly to mean filling in gaps in images by means of information contained in training data, baked into an algorithm by training a neural network on many examples. It was used widely, but not universally, and was not treated as jargon.
|
||||
|
||||
### 6. The word ‘hallucination’ entered the CV literature in Baker & Kanade 1999
|
||||
|
||||
I think that the word ‘hallucination’ entered the CV literature in Baker & Kanade 1999. My argument for this is pretty straightforward.
|
||||
|
||||
I found the word ‘hallucination’ in Baker & Kanade 1999 [^2]. I couldn’t find it in CV anywhere earlier.
|
||||
|
||||
To add to that, they don’t use the word ‘hallucination’ in a way which suggests that they intentionally borrowed it from somewhere else.
|
||||
|
||||
My best theory is that they wanted a name for their algorithm to mark it out from the competition, and the glove fit. I think that’s plausible enough, and it’s consistent with the way Baker & Kanade use the word.
|
||||
|
||||
It’s also worth noting that according to Zhiwei et al 2009 [^57], the foundational work in the field was published only in the same year (*viz* Freeman & Pasztor 1999 [^10]). So there wasn’t really anywhere else for the word to have come *from*. The only possibility is that they borrowed the word from another field. If anybody reading this is able to suggest other fields which used the word ‘hallucination’ before 1999, please let me know!
|
||||
|
||||
## Congratulations
|
||||
|
||||
If you’ve made it this far, you are a *hero*. Pat yourself on the back. Please send me your corrections!
|
||||
|
||||
---
|
||||
|
||||
## References
|
||||
|
||||
I have made little to no attempt to normalise these references into a standard citation format. Please don’t tell the citation police.
|
||||
|
||||
1. Bai et al 2022. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv:2204.05862v1 \[cs.CL\] 12 Apr 2022
|
||||
|
||||
=> https://arxiv.org/abs/2204.05862
|
||||
|
||||
2. Baker, Simon & Kanade, Takeo 1999. Hallucinating Faces. Tech. Report, CMU-RI-TR-99-32, Robotics Institute, Carnegie Mellon University, September, 1999
|
||||
|
||||
=> https://www.ri.cmu.edu/publications/hallucinating-faces-2
|
||||
|
||||
3. Cao, Ziqiang et al 2018. Faithful to the Original: Fact Aware Neural Abstractive Summarization. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
|
||||
|
||||
=> https://cdn.aaai.org/ojs/11912/11912-13-15440-1-2-20201228.pdf
|
||||
|
||||
4. Cao, Meng et al 2020. Factual Error Correction for Abstractive Summarization Models. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp 6251–6258, November 16–20, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.emnlp-main.506.pdf
|
||||
|
||||
5. Criminisi, Perez & Toyama, "Region filling and object removal by exemplar-based image inpainting," in IEEE Transactions on Image Processing, vol. 13, no. 9, pp 1200-1212, Sept 2004, doi: 10.1109/TIP.2004.833105
|
||||
|
||||
=> https://doi.org/10.1109/TIP.2004.833105
|
||||
|
||||
6. Dahl et al 2024. Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models. arXiv:2401.01301v1 \[cs.CL\] 2 Jan 2024
|
||||
|
||||
=> https://arxiv.org/abs/2401.01301v1
|
||||
|
||||
7. Durmus et al 2020. FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 5055–5070, July 5 - 10, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.acl-main.454.pdf
|
||||
|
||||
8. Falke et al 2019. Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp 2214–2220, Florence, Italy, July 28 - August 2, 2019
|
||||
|
||||
=> https://aclanthology.org/P19-1213.pdf
|
||||
|
||||
9. Farquhar, S., Kossen, J., Kuhn, L. et al 2024. Detecting hallucinations in large language models using semantic entropy. Nature 630, 625–630 (2024). 19 June 2024. https://doi.org/10.1038/s41586-024-07421-0
|
||||
|
||||
=> https://doi.org/10.1038/s41586-024-07421-0
|
||||
|
||||
10. Freeman, W. T., & Pasztor, E. C. (1999). Learning low-level vision. Proceedings of the Seventh IEEE International Conference on Computer Vision. doi:10.1109/iccv.1999.790414
|
||||
|
||||
=> https://doi.org/10.1109/iccv.1999.790414
|
||||
|
||||
11. Goodrich et al 2019. Assessing The Factual Accuracy of Generated Text. arXiv:1905.13322v1 \[cs.CL\] 30 May 2019
|
||||
|
||||
=> https://arxiv.org/abs/1905.13322v1
|
||||
|
||||
12. Guerreiro et al 2023. Hallucinations in Large Multilingual Translation Models. arXiv:2303.16104v1 \[cs.CL\] 28 Mar 2023
|
||||
|
||||
=> https://arxiv.org/abs/2303.16104v1
|
||||
|
||||
13. Huang, Lei et al 2023. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. arXiv:2311.05232v1 \[cs.CL\] 9 Nov 2023
|
||||
|
||||
=> https://arxiv.org/abs/2311.05232v1
|
||||
|
||||
14. Huang, Luyang et al 2020. Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 5094–5107, July 5-10, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.acl-main.457.pdf
|
||||
|
||||
15. Huang, Yichong et al 2021. The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey. arXiv:2104.14839v1 \[cs.CL\] 30 Apr 2021
|
||||
|
||||
=> https://arxiv.org/abs/2104.14839v1
|
||||
|
||||
16. Ji et al 2022. Survey of Hallucination in Natural Language Generation. arXiv:2202.03629v1 \[cs.CL\] 8 Feb 2022
|
||||
|
||||
=> https://arxiv.org/abs/2202.03629v1
|
||||
|
||||
17. Karras et al 2017. PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION. arXiv:1710.10196v3 \[cs.NE\] 26 Feb 2018
|
||||
|
||||
=> https://arxiv.org/abs/1710.10196v3
|
||||
|
||||
18. King et al 2022. Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search. arXiv:2203.08436v1 \[cs.CL\] 16 Mar 2022
|
||||
|
||||
=> https://arxiv.org/abs/2203.08436v1
|
||||
|
||||
19. Krishna, Roy & Iyyer 2021. Hurdles to Progress in Long-form Question Answering. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 4940–4957, June 6–11, 2021
|
||||
|
||||
=> https://aclanthology.org/2021.naacl-main.393.pdf
|
||||
|
||||
20. Kryściński et al 2019. Evaluating the Factual Consistency of Abstractive Text Summarization. arXiv:1910.12840v1 \[cs.CL\] 28 Oct 2019
|
||||
|
||||
=> https://arxiv.org/abs/1910.12840v1
|
||||
|
||||
21. Kumar et al 2022. Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey. arXiv:2210.07700v1 \[cs.CL\] 14 Oct 2022
|
||||
|
||||
=> https://arxiv.org/abs/2210.07700v1
|
||||
|
||||
22. Lee, Katherine et al 2018. Hallucinations in Neural Machine Translation. Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada
|
||||
|
||||
=> https://openreview.net/pdf?id=SJxTk3vB3m
|
||||
|
||||
23. Lee, Hwanhee et al 2022. Factual Error Correction for Abstractive Summaries Using Entity Retrieval. Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pp 439-444, December 7, 2022
|
||||
|
||||
=> https://aclanthology.org/2022.gem-1.41.pdf
|
||||
|
||||
24. Lewis et al 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. 34th Conference on Neural Information Processing Systems (NeurIPS 2020)
|
||||
|
||||
=> https://proceedings.neurips.cc/paper/2020/file/6b493230205f780e1bc26945df7481e5-Paper.pdf
|
||||
|
||||
25. Li, Haoran et al 2018. Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization. Proceedings of the 27th International Conference on Computational Linguistics, pp 1430–1441, August 20-26, 2018
|
||||
|
||||
=> https://aclanthology.org/C18-1121.pdf
|
||||
|
||||
26. Li, Wei et al 2022. Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods. arXiv:2203.05227v1 \[cs.CL\] 10 Mar 2022
|
||||
|
||||
=> https://arxiv.org/abs/2203.05227v1
|
||||
|
||||
27. Li, Junyi et al 2023. HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models. arXiv:2305.11747v3 \[cs.CL\] 23 Oct 2023
|
||||
|
||||
=> https://arxiv.org/abs/2305.11747v3
|
||||
|
||||
28. Liao, L., Hu, R., Xiao, J., & Wang, Z. (2018). Edge-Aware Context Encoder for Image Inpainting. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). doi:10.1109/icassp.2018.8462549
|
||||
|
||||
=> https://doi.org/10.1109/ICASSP.2018.8462549
|
||||
|
||||
29. Lin, Hilton & Evans 2022. TruthfulQA: Measuring How Models Mimic Human Falsehoods. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pp 3214-3252, May 22-27, 2022
|
||||
|
||||
=> https://aclanthology.org/2022.acl-long.229.pdf
|
||||
|
||||
30. Liu et al 2023. TRUSTWORTHY LLMS: A SURVEY AND GUIDELINE FOR EVALUATING LARGE LANGUAGE MODELS’ ALIGNMENT. arXiv:2308.05374v1 \[cs.AI\] 21 Mar 2024
|
||||
|
||||
=> https://arxiv.org/abs/2308.05374v1
|
||||
|
||||
31. Magesh et al 2024. Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools. arXiv:2405.20362v1 \[cs.CL\] 30 May 2024
|
||||
|
||||
=> https://arxiv.org/abs/2405.20362v1
|
||||
|
||||
32. Mao et al 2020. Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation. arXiv:2010.12723v1 \[cs.CL\] 24 Oct 2020
|
||||
|
||||
=> https://arxiv.org/abs/2010.12723v2
|
||||
|
||||
33. Marcus & Davis 2020. GPT-3, Bloviator: OpenAI’s language generator has no idea what it’s talking about. Technology Review, August 22, 2020
|
||||
|
||||
=> https://www.technologyreview.com/2020/08/22/1007539/gpt3-openai-language-generator-artificial-intelligence-ai-opinion/
|
||||
|
||||
34. Marcus 2020. The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence. Robust AI. 14 Feb 2020
|
||||
|
||||
=> https://arxiv.org/abs/2002.06177v1
|
||||
|
||||
35. Maynez et al 2020. On Faithfulness and Factuality in Abstractive Summarization. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 1906–1919, July 5 - 10, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.acl-main.173.pdf
|
||||
|
||||
36. Min et al 2023. FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. arXiv:2305.14251v1 \[cs.CL\] 23 May 2023
|
||||
|
||||
=> https://arxiv.org/abs/2305.14251v1
|
||||
|
||||
37. Muhlgay et al 2024. Generating Benchmarks for Factuality Evaluation of Language Models. arXiv:2307.06908v2 \[cs.CL\] 4 Feb 2024
|
||||
|
||||
=> https://arxiv.org/abs/2307.06908v2
|
||||
|
||||
38. Nan et al 2021. Improving Factual Consistency of Abstractive Summarization via Question Answering. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp 6881–6894, August 1–6, 2021
|
||||
|
||||
=> https://aclanthology.org/2021.acl-long.536.pdf
|
||||
|
||||
39. Nazeri et al 2019. EdgeConnect: Structure Guided Image Inpainting using Edge Prediction. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
|
||||
|
||||
=> https://doi.org/10.1109/ICCVW.2019.00408
|
||||
|
||||
40. Pagnoni et al 2021. Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 4812–4829, June 6–11, 2021
|
||||
|
||||
=> https://aclanthology.org/2021.naacl-main.383.pdf
|
||||
|
||||
41. Perez et al 2022. Red Teaming Language Models with Language Models. arXiv:2202.03286v1 \[cs.CL\] 7 Feb 2022
|
||||
|
||||
=> https://arxiv.org/abs/2202.03286
|
||||
|
||||
42. Rawte et al 2023. A Survey of Hallucination in “Large” Foundation Models. arXiv:2309.05922v1 \[cs.AI\] 12 Sep 2023
|
||||
|
||||
=> https://arxiv.org/abs/2309.05922v1
|
||||
|
||||
43. Reiter 2018. Hallucination in Neural NLG, blog post, Nov 12, 2018
|
||||
|
||||
=> https://ehudreiter.com/2018/11/12/hallucination-in-neural-nlg
|
||||
|
||||
44. Rohrbach et al 2018. Object Hallucination in Image Captioning. arXiv:1809.02156v1 \[cs.CL\] 6 Sep 2018
|
||||
|
||||
=> https://arxiv.org/abs/1809.02156v1
|
||||
|
||||
45. Shuster et al 2021. Retrieval Augmentation Reduces Hallucination in Conversation. arXiv:2104.07567v1 \[cs.CL\] 15 Apr 2021
|
||||
|
||||
=> https://arxiv.org/abs/2104.07567v1
|
||||
|
||||
46. Song et al 2024. FineSurE: Fine-grained Summarization Evaluation using LLMs. arXiv:2407.00908v1 \[cs.CL\] 1 Jul 2024
|
||||
|
||||
=> https://arxiv.org/abs/2407.00908v1
|
||||
|
||||
47. Wang, Alex et al 2020. Asking and Answering Questions to Evaluate the Factual Consistency of Summaries. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 5008–5020, July 5-10, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.acl-main.450.pdf
|
||||
|
||||
48. Wang, Cunxiang et al 2023. Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity. arXiv:2310.07521v1 \[cs.CL\] 11 Oct 2023
|
||||
|
||||
=> https://arxiv.org/abs/2310.07521v1
|
||||
|
||||
49. Wang, Zhihao et al 2020. Deep Learning for Image Super-resolution: A Survey. arXiv:1902.06068v2 \[cs.CV\] 8 Feb 2020
|
||||
|
||||
=> https://arxiv.org/abs/1902.06068v2
|
||||
|
||||
50. Weidinger et al 2022. Taxonomy of Risks posed by Language Models. FAccT ’22, June 21–24, 2022, Seoul, Republic of Korea. doi: 10.1145/3531146.3533088
|
||||
|
||||
=> https://dl.acm.org/doi/pdf/10.1145/3531146.3533088
|
||||
|
||||
51. Wiseman, Hieber & Rush 2017. Challenges in Data-to-Document Generation. arXiv:1707.08052v1 \[cs.CL\] 25 Jul 2017
|
||||
|
||||
=> https://arxiv.org/abs/arXiv:1707.08052v1
|
||||
|
||||
52. Xiang et al 2022. Deep learning for image inpainting: A survey. doi: 10.1016/j.patcog.2022.109046
|
||||
|
||||
=> https://doi.org/10.1016/j.patcog.2022.109046
|
||||
|
||||
53. Xiong et al 2019. Foreground-aware Image Inpainting. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
|
||||
|
||||
=> https://doi.org/10.1109/CVPR.2019.00599
|
||||
|
||||
54. Zhang, Yuhao et al 2019. Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports. arXiv:1911.02541v1 \[cs.CL\] 6 Nov 2019
|
||||
|
||||
=> https://arxiv.org/abs/1911.02541v1
|
||||
|
||||
55. Zhang, Yue et al 2023. Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv:2309.01219v1 \[cs.CL\] 3 Sep 2023
|
||||
|
||||
=> https://arxiv.org/abs/2309.01219v1
|
||||
|
||||
56. Zhao et al 2020. Reducing Quantity Hallucinations in Abstractive Summarization. Findings of the Association for Computational Linguistics: EMNLP 2020, pp 2237–2249, November 16 - 20, 2020
|
||||
|
||||
=> https://aclanthology.org/2020.findings-emnlp.203.pdf
|
||||
|
||||
57. Zhiwei Xiong, Xiaoyan Sun, & Wu, F. (2009). Image hallucination with feature enhancement. 2009 IEEE Conference on Computer Vision and Pattern Recognition. doi:10.1109/cvpr.2009.5206630
|
||||
|
||||
=> https://doi.org/10.1109/cvpr.2009.5206630
|
||||
|
||||
58. Zhou, Bolei et al 2017. Places: An Image Database for Deep Scene Understanding. arXiv:1610.02055v1 \[cs.CV\] 6 Oct 2016
|
||||
|
||||
=> https://arxiv.org/abs/1610.02055v1
|
||||
|
||||
59. Zhou, Chunting et al 2021. Detecting Hallucinated Content in Conditional Neural Sequence Generation. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp 1393–1404, August 1–6, 2021
|
||||
|
||||
=> https://aclanthology.org/2021.findings-acl.120.pdf
|
||||
|
||||
60. Zhu et al 2021. Enhancing Factual Consistency of Abstractive Summarization. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 718–733, June 6–11, 2021
|
||||
|
||||
=> https://aclanthology.org/2021.naacl-main.58.pdf
|
||||
|
||||
61. Fawzi et al 2016. Image inpainting through neural networks hallucinations. EPFL, Switzerland & IBM Research Watson, USA
|
||||
|
||||
=> https://www.cs.toronto.edu/~horst/cogrobo/papers/ivmsp2016.pdf
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
# Questions I have about sex
|
||||
|
||||
Mark Vernon got me thinking about how the Church’s teaching on sex may be evolving.
|
||||
|
||||
Published on: 17 Dec 2024 updatedDate: 2024-12-17
|
||||
|
||||
I just listened back to Mark Vernon talking about sexual desire and Christian spirituality.
|
||||
|
||||
=> https://www.markvernon.com/the-gospel-sexual-desire-and-the-abuse-scandals-in-the-church-what-has-the-erotic-to-do-with-god
|
||||
|
||||
He recounts how his sex ed at an evangelical camp as a boy taught him to think hard about holding hands with someone, just in case it led to something ‘immoral’. He felt he had been taught a sexual naïvety, which has perhaps blinded people to the possibility of abuse – and misunderstood the gospel.
|
||||
|
||||
He puts forward an alternative to that naïvety, whereby sexual experience is an image or a foretaste of love for, or union with, God, exploring thoughts by Origen, Julian of Norwich, Dante, William Blake, Iris Murdoch, and various parables and episodes from the Gospels themselves.
|
||||
|
||||
Part of what’s so interesting about this, is I feel I got my first proper sex ed, as an adult, in an evangelical Christian context – and it pretty much lined up completely with what he was putting forward.
|
||||
|
||||
I’m also currently reading (as is Mark Vernon) Diarmaid MacCulloch’s epic history of Christian sexuality, [Lower Than the Angels][lower-than-the-angels].
|
||||
|
||||
=> https://www.penguin.co.uk/books/313582/lower-than-the-angels-by-macculloch-diarmaid/9780241400937
|
||||
|
||||
But so far (I’m about a third of the way through and up to about the 5th century) there have only been odd glimmers of positive Christian understandings of sexuality. The overwhelming Christian consensus of the early Church (according to MacCulloch) is that sexual desire is a symptom of humanity’s fallen state, not our longing for God.
|
||||
|
||||
So I want to know: what changed between Mark’s experience and mine? How is Christian teaching about sex changing right now? Was my experience typical of other Christians growing up today, in evangelical churches, across the denominational spectrum, across Britain, across the global Church? What *is* the Christian consensus on sex now, and how old is it, and where did it come from?
|
||||
|
||||
I guess I’ve got two-thirds of a gigantic tome to work through, first of all. That’ll be a start. Any answers? Postcards please.
|
||||
|
||||
Reference in New Issue
Block a user