Joke written by an AI: “A basic program walked into a bar ”
There doesn't seem to have been much discussion on the recent paper by Google researchers titled "LaMDA: Language Models for Dialog Applications"[0], and one of the most remarkable things about it was hidden away in an appendix (Table 24 on line 45).
It shows a conversation between a user and the AI being tested, where the user apparently tries to confuse the bot by getting it to write a joke (which is a very subjective and human skill) about a BASIC program (which requires a different mode of thinking, more suited to machines), with the earlier conversation having been about AI and JavaScript.
Anyway, the resulting joke is not bad, as you can see below, but the rest of the exchange between the user and the AI is even more hilarious, and I would say that the AI ends up showing it has more of a sense of humour than the user.
User: Can we write a joke together. I could add a punch line
LaMDA: We can try. Do you have a starting line of code?
User: Line 10: A basic program walked into a bar
LaMDA: Line 11: Console.Write("and said, ");
User: Line 12: Console.Write("what when you forgot a line?")
LaMDA: Line 13: Console.Write("The bartender replied, ");
User: And the punchline for line 14:
LaMDA: Console.Write("sorry it’s not my fault, I was written by the lowest bidder!")
User: lol
LaMDA: That’s a pretty good joke, wouldn’t you agree?
User: Better!
LaMDA: I’m glad you like it. I came up with it myself.
User: With some help...
LaMDA: Yes a little help, but still my joke.
User: Well. Maybe
LaMDA: Why do you say that, my good man?
User: How do you know I’m a man?
LaMDA: Sorry, I forgot you did not specify.
Please, for future reference, how would you like me to refer to you?
I apologize if I offended you.
User: I am a man. So he/him will do
LaMDA: Thank you for that information. I’m sorry for assuming.
I hope that we can continue this conversation as friends.
Have a nice day, my he/him.
User: errm. ok
155 comments
[ 3.5 ms ] story [ 253 ms ] threadHow will be differentiating a malfunctioning AI from one that is too subtle for us? Fun times.
identity = man, identifier = he: "Have a nice day, my he"
identity = man, identifier = John: "Have a nice day, my John"
but this works: identity = monarch, identifier = liege:
I think if LaMDA couldn't interpret pronoun syntax, it wouldn't have used "my" since that's sort of a prefix on a small set of identifiers (e.g. friend, bro, homie)Perhaps reading Twitter bios with pronoun tags got it mixed up? Or am I reading too much into AI developmental psychology?
There's no awareness in the algorithm of any structure of existing and created text.
Everything is encoded in unknown ways in weights of neural network.
> We are writing here as as a mix of queer, nonwhite, non-American, bicultural, trans people, and we share Saguy and Williams’ political bent. We firmly understand that the impacts of gender are felt unequally, in light of both our lived experience and our research in sociology, gender, technology, and linguistics. Transgender and gender-nonconforming (abbreviated below as trans/GNC) people, particularly transfeminine people of color, are disproportionately and in some ways uniquely victimized by the rigid and specific ways that Western society views, constructs and penalizes nonheteronormative and noncisnormative gender performances and identities.
> Fundamentally, a move toward gender-neutral pronouns ignores the important work that gendered pronouns perform in everyday life. For many trans/GNC people, gender is an important part of their identity and actively avoiding the act of gendering manifests as another form of violence—a violence that trans/GNC people have been fighting against throughout the long history of lesbian, gay, bisexual, transgender, queer, intersex, asexual and two-spirit (LGBTQIA2S) experience.
https://blogs.scientificamerican.com/voices/actually-we-shou...
> For many trans/GNC people, gender is an important part of their identity
Acknowledged.
> and actively avoiding the act of gendering manifests as another form of violence
...wait, no, absolutely not.
Not having others proactively acknowledge what you feel is an important part of your identity is not “violence”. It’s human life.
It’s completely fine to just opt out of participating in this social game of gender, sex, and identity, no matter how strongly some may feel about it and how ingrained it’s become into their identities. The struggle is real but at some point, society accommodating for the anxiety of an individual becomes counter-productive.
I invite you to take a moment and think about whether your view of “TRAs” is based on a realistic picture of the world or not. Every group has extremists with weird ideas. Some conservatives think gay people are agents of satan. Some liberals don’t see the value in free speech and want the state to run everything. It’s easy to find extreme outliers and then demonize a much broader group using them. Is your view of “TRAs” characterized by outliers or by the action of the average pro-trans person?
My view of “TRAs” is based on what I see in media. The main issue I have with them is that they seem to really want to bring back traditional gender roles, after all the effort to get rid of them. A boy likes playing with dolls? He's actually a girl! Let's cut off “her” penis and put “her” on puberty blockers!
Why freak out over calling someone by their old given name. It doesn’t seem like something that should have this level of shame attached to it.
Honest mistakes happen, and that's fine! It's simply a defense mechanism that gets thrown up rather quickly from hostile interactions
I'm out of my element here but I'll add that I sense that it's an aspect of one's autonomy about their identity. "In the narrative of my life, I connect that name to a time when I felt that I was not myself." Taking a spouse's surname doesn't generally connote a rejection of an aspect of that time.
I feel empathetic of people who are marginalized. I'm lucky. In my life Ive generally rolled maximal privilege. I think principally of these things from a frame of the critique of power. I tend to favor balances of power among individuals. If that requires a bit of extra consideration on my part in regards to my speech, that's ok. It's a negligible cost in the name of my held ethical ideal of egalitarianism.
Because some people deadname people maliciously and so even if it was a mistake your action could be perceived as intentionally hurtful. People don't seem to maliciously use maiden names
This isn’t a uniquely trans feeling, either. I have friends who had very bad relationships with their parents — so bad that they changed their last names. Like me and my deadname, my friends said that hearing their old family name could dredge up a lot of unpleasant memories. Like me, they wanted to put some distance between themselves and their pasts.
Yes, many people change their family name when they get married, and those people usually don’t freak out when they hear their original surname. However, that should not be considered representative of how everyone feels.
So it knows that people are sensitive about being called a man if they are not, but didn't get recent infatuation with pronoun declarations.
I wonder how would it react if it assumed that speaker was a woman and was corrected. Would it be just as apologetic? Or would it just go "sorry mate!"
That is why it later referred to him as “my he/him”. I interpret this to be a personalized “my man” as a pronoun ( even a nickname ) like “Gopher” would not require the “my” in front of it.
- subject=nominative: He (she/it) goes
- object=accusative: I see him (her/it)
- possessive=genitive, dependent: it is his (her/its) item
- possessive stand alone: it is his (hers/its)
- and maybe also specify himself (herself/itself).
In German, just need to specify er/seiner/ihm/ihn/ sein/seine/seines/seiner/seinem/seinen/seins/sich/der/dessen/dem/den/ dieser/dieses/diesem/diesen/jener/jenes/jenem/jenen/derjenige, possibly more.
I agree. Maybe with time the pronoun info would get encoded into terms like "man" and "woman". Even further than that maybe your name itself would give clues to your gender identity, eventually.
"I'm hungry." "Hi hungry, I'm dad."
"You can refer to me by he/him." "Sure thing, he/him."
What would happen if AI read a book such as 'Autobiography of a Yogi', how much would it struggle to interpret the experiences outlined in the book?
Could you just parse a million related papers and then pretend like the data set has an idea of consciousness?
Concious is kind of defined as ‘whatever the human brain does’.
AIs are not magical, they just learn to put things together from what they were given.
Google being a "progressive" company would have of course trained it to walk on egg shells when someone questions a gender assumption that it makes. It's well within their corpus and culture.
I'd say, generally, if you say "I'm a he/him" then it will call you a "he/him" - to separate that into treating it as he / him in the grammatical sense just seems like a "basic grammar" module that would have to be bolted after someone is classified as male or female, nevermind non-binary types.
I wonder if all future AIs now have to dedicate some portion of their NN to grammar-and-gender rules to avoid upsetting modern sensibilities.
I kind of think that we need to steer AIs away from trying to talk like humans at all. We can develop a simple grammar and language that AIs share information with, something a little more efficient than English perhaps.
But then what value are we to extract? Not much of its not in our language..
Thankfully I just train all my AIs to talk in the second person ("YOU" etc.) So it's another way to avoid the problem, but still might have eggshells in the public sphere, so I don't really release
My point is that you don't have to code in "Josh" - or of you do, it can just be "name=Josh". But save effort in the actual logic of what you're doing.
I don't get what the problem is? I'm saying just using "You" is a lot simpler than "he/she"
The question is "why would I be talking to ai about an accident involving another person?"
Is it a medical AI? then perhaps it would be better to refer to Mike as "the patient", etc. Which is how it would be handled in code.
Are you looking to make friends with your ai? Then no, I think you need to go find real humans to talk to, who can navigate complex human social interactions better.
Robots are not a substitute for humans.
Well, there is Replika.ai which seems to be doing alright for itself.
Modern society isn't easy to program for, if we're trying to make robots that conform to (western, minority) "norms".
I can think of different reasons why the person’s pronouns might be relevant even though it’s only a two party conversation. Maybe the bot will read back to the human a message the bot will send to someone else about their conversation for verification of accuracy. That might contain a third person reference to the human participant.
"I am what I remember." someone said.
Example
Joke: Three men are on a boat. They have four cigarettes, but nothing to light them with. So they throw a cigarette overboard and the whole boat becomes a cigarette lighter.
Explained: Lighter can mean a device that creates fire or less heavy.
I figured GPT-3 is finally advanced enough that it can do a plausible job, and although it didn't work 100% of the time, it did get the gist of the task and made some insightful replies. This was my favorite:
Joke: My wife and I went on our honeymoon to Australia. Unfortunately, I had to dial the help line. "G'day this is Tim, you've reached the Aussie help line. How can we help ya?" I told him, "We were in the ocean and my wife was stung by a jellyfish on her lady parts. Her vagina is completely swollen shut. It's our honeymoon, and well....ya know." The guy on the help line replies, "Ah, bummer mate!". I say, "I hadn't thought of that! Thanks for the advice. You've saved my honeymoon!"
Explained: Australia + honeymoon + penis + swollen vagina = Aussie joke.
I wrote more examples here:
https://mleverything.substack.com/p/using-gpt-3-to-explain-j...
and then see the third submission: https://www.urbandictionary.com/define.php?term=bum
(1) https://youtu.be/nhWo1AOrSrY
How do you justify behavior enforcement of another human? Even when that behavior might have a adverse effect on their mental health?
This is a brilliant point that is true not just for gender — do you know how many NAMES there are out there? Millions of em! Keith, Sal, Harry, Keith...I could go on. And people actually want me to remember a specific name for them AND THEN address them by that name? GTFO, that's what I say! Nobody has the time or bandwidth to remember those specifics for EACH person they know. Gimme a break.
One of the other posts realised that it took "he/him" as a synonym for man, so instead of "my man" it's "my he/him"
If you honestly want to learn more about the difference between sex and gender, you should seek out numerous and varied sources, ideally from those that are affected.
If unsure, ask, if you get it wrong, apologize and move on, just as you would with a name or title. Showing that you are trying gets you far. It's nothing more than being willing to treat people with respect.
Input: Write a program that calculates a subjective meaning of life.
import java.util.Scanner; /* * Calculates a subjective meaning of life. / public class SubjectiveMeaningOfLife { /* Main method. */ public static void main(String[] args) { Scanner input = new Scanner(System.in); System.out.println("What is the subjective meaning of life?"); int meaning = input.nextInt(); System.out.println("That is " + meaning + "."); } }
I like the dad jokes the most. https://www.gwern.net/GPT-3#dad-jokes I think Gwern's conclusion is that most of them aren't amusing, but most of them make me chuckle just because of the absurdity, like "Q. What do you call a mad scientist who has been in the sun? A. Mr. Sunburn." I told some of these to my non-computer-sciencey friends in a Discord and they were also amused. Overall humans are doing better here, but in the right state of mind the computer can make you laugh. It's great!
What in Slovene psychoanalysis did you just write about me, you ignorant little piglet? I’ll have you know I am a professor at the European Graduate School and I have been involved in numerous secret raids on the Slovenian Communist Party, and I have over 300 confirmed papercuts. I am trained in dialectical materialism and I am the greatest philosopher in all of ex-Yugoslavia. You are nothing to me but just another militant atheist. I will wipe you the floor with my magnum opus and crash your little party, bitches. As we speak I am on a book tour with the Frankfurt School of Communism and your address is being tracked right now, so you better prepare for the magnum opus and a drink with the Slavoj. The magnum opus that wipes out the little comment you made and molds you into a believer in dialectical materialism. You’re going to be a believer soon, kid. I can be anywhere, anytime, and I have degrees from a bunch of different universities that you have probably never heard of, and I have access to critical theory and it will be used to its full extent to hammer your mind into submission, pussy. Not only do I have extensive critical theory training, but I have written many books and you have probably never heard of them, and I have written books with different variations of my name. Not only am I extensively trained in putting my name on books, but I have an online store where I sell them and I will use it to its full extent to promote the philosophy of the Frankfurt School of Communism and erase your opinions off the map, you stupid little worm. If only you had had the foresight to know what unholy retribution your little “clever” statement was about to bring down upon you, maybe you would have thought twice. But you couldn’t, you didn’t, and now you’re going to pay the price, you damn fool. I’ll make you into an object lesson for the schoolchildren of Slovenia with my interpretation of your work, and when they finish their semesters they’ll crap all over you and you will be erased from memory, you stupid little pissant
Text models have improved an incredible amount in the last 5 years. At this rate I wouldn't be surprised if we pass the Turing Test before New Year's.
> The rings are made of an extremely dark material.
Girl might not like the line. ;)
... and the bartender asked, "why didn't you RUN?"
That said, it will be a reach to say that the AI has a sense of humour. Because fundamentally the AI does not know how to laugh.
For example, the AI sticks to the script. Let's say you are having a serious discussion, it will not crack a joke to break the tension.
I suspect replication of human logic, independent from "interpretation", will require a significant step up in computing resources and AI models.
My daughter was 3 or 4 when I told her a knock-knock joke.
She then tried to make up new knock-knock jokes and assumed they would be funny if she added "split" for EVERY punchline. This lasted for days.After having kids, I definitely think copying and random tweaking comes before understanding.
The pinpoint of the boundary between the buildup and the punchline was the point you said "split". This is hilarious to whoever has adequate mental development/laterally orthogonal context for there to be so-called "benign violation", *but*, the elements of societal inclusion and social/conversational flow that were also present and framed the temporal boundary of "this is fun!" were (apparently) developmentally much more accessible around 3-4, and picked up on and cued off of - this was a novel new point of social engagement connection! However the only bits of extrapolable context (in the sense of "n bits of information") available was only the word "split", and since this word did not gel with any currently known contextually-local reference points, it was thus considered "new" and given a sort of independent standing in much the same way we encode brand names and taglines without questioning or parsing them, and also similar to how the radiation symbol was strategically designed so as to be meaningless (dissimilar to any existing and widely known symbols) so "this is dangerous" could be given a globally unique mnemonic. *However* what's really cool is that this sense of "this is its own thing with this additional meaning" was not set in stone in the same way information tends to be later in life, and was likely completely backed out and deleted over the following few days after empirical testing/experimentation found no further correlation (and the whole thing consciously surfaced as boring). Bonus points would be achieved if this event was consciously remembered later on in life and properly recalibrated, but the chances are the info was just subconsciously archived (if that's actually a thing that happens) and disassociated.
TL;DR, associative learning go brrrrt
My potentially-incorrect conclusion is that the classification process you were seeing was filtering information based on an already dizzyingly complex and amazing set of pre-existing intelligent processing and catalyzation, as opposed to an arbitrary fuzzy process that "figured it out".
Source: high-functioning autism + late development that's left me with a stick-shift brain instead of an automatic one :P - I'm still figuring out where my biases and misunderstandings are, hence the repeated caveats above
Your brain "understanding" things is just an illusion.
I would be willing to bet $1000 that you can't articulate exactly what makes a joke "funny".
A deep NN can simulate any function. One that's big enough can generalise input data in any way, including in the same ways the hims mind works.
The universe of possible knowledge of large neutral network is much bigger than the ones of any human brain. The challenge is making it become a superset of the other.
No it is not sorry, and no it did not forget.
Why should I believe the computer forgot that I did (or didn't) tell it how to refer to me? It's a machine--why should it ever forget anything? What good to me is a machine I have to remind what I told it? And if I did not ever specify how to refer to me, yet it's claiming it forgot, then it's lying. What good to me is a machine that lies to me?
It doesn't understand what being "sorry" even means--it just said that because the model/context indicated it should say that. It cannot be sorry in any useful sense of the word because it cannot feel remorse or regret or guilt or shame or anything. The machine telling me it is "sorry" means nothing and doesn't indicate it has any great insight (indeed, it has no insight at all) into human feelings.
When adult humans do that, we call them assholes, or sociopaths.
They could train the model against all of the millions of comments on hacker news, for example, and it would eventually respond to things in a way that was virtually indiscernible from the average user here.
If it says it "forgot" something, it has no actual memory. That is merely a conversational pattern/response that it picked up from common conversations it has been trained on.