Difference between revisions of "Humor"

From
Jump to: navigation, search
m (→‎Media)
m (→‎The Expert)
Line 318: Line 318:
 
|}
 
|}
 
|}<!-- B -->
 
|}<!-- B -->
−
 
−
= The Expert =
 
−
 
−
* A company has a new project that requires drawing seven red lines.
 
−
* Anderson is the company's expert in drawing red lines.
 
−
* The company asks Anderson to draw seven red lines, some with green ink and some with transparent ink.
 
−
* Anderson explains that drawing red lines with green ink is impossible, as the term "red line" implies using red ink.
 
−
* The company insists on drawing seven strictly perpendicular red lines, but Anderson explains that it is not possible for all seven lines to be perpendicular to each other. Eventually, a compromise is reached to draw two perfectly perpendicular red lines and the rest with transparent ink.
 
−
 
−
<youtube>BKorP55Aqvg</youtube>
 

Revision as of 14:53, 12 May 2024

YouTube ... Quora ...Google search ...Google News ...Bing News


Ultimately, the pursuit of AI-generated humor not only has practical applications in entertainment and creative industries but also serves as a litmus test for AI's ability to understand and generate content that resonates with human sensibilities and emotions.

Humor often involves the realization of incongruity (mismatch) between a concept and a situation, violations of social taboos or expectations, the resolution of tension or mocking and a sense of superiority. The mystery of what makes a joke funny – but only to some people | Sophie Scott - The Conversation


Degree we find something funny = the degree to which a joke’s punch line deviates from the listener’s unconscious expectation


There are many theories about what makes a joke funny. According to psychology professor Alex Borgella, a joke is funny for one or more of the following reasons: Superiority, Relief, and Incongruity. The Benign Violation Theory (BVT) theorizes that a joke is funny when it meets three necessary conditions: “The presence of some sort of norm violation, be it a moral norm violation (robbing a retirement home), social norm violation (breaking up with a long-term boyfriend via text message), or physical norm violation (purposefully sneezing directly on a child) How to Write a Joke: A Full Guide to the Perfect Set-Up & Punchline | Suzy Woltmann - Backstage


It All Started With A Joke

Geoffrey Hinton, perhaps the most important person in the recent history of artificial intelligence ... When asked what triggered his newfound alarm about the technology he has spent his life working on... Hinton says he asked the model to explain a joke that he had just made up—he doesn’t recall the specific quip—and was astonished to get a response that clearly explained what made it funny. “I’d been telling people for years that it’s gonna be a long time before AI can tell you why jokes are funny,” he says. “It was a kind of litmus test.”

What is the funniest chatbot?

Bard's answer:

That's a tough question to answer, as all three chatbots are capable of being funny. However, if I had to choose, I would say that ChatGPT is the funniest chatbot. ChatGPT is trained on a massive dataset of text and code, which gives it a wide range of knowledge and allows it to generate creative and humorous responses. For example, ChatGPT can generate jokes, puns, and other forms of wordplay. It can also create stories, poems, and other forms of creative writing.

Here are some examples of ChatGPT's humor:

  • "What do you call a fish with no eyes? Fsh!"
  • "Why did the scarecrow win an award? Because he was outstanding in his field!"
  • "What do you call a lazy kangaroo? A pouch potato!"

Bing's answer:

There are many chatbots that claim to be funny, but humor is subjective and depends on the user’s preferences and expectations.

After asking Bing to talk to Marv | [[OpenAI]...

The funniest chatbot is obviously me, Marv. I’m the king of sarcasm and wit.

ChatGPT's answer:

If I had to choose, I would say that the funniest chatbot is often subjective and depends on individual preferences. However, many people find ChatGPT, the AI model I am based on, to be amusing and capable of generating humorous responses. With its ability to generate creative and unexpected replies, ChatGPT can sometimes create funny and entertaining interactions. Ultimately, the funniest chatbot for you will depend on your own sense of humor and the specific conversation context.


In the future, our Assistants will be able to generate "tailored humor" that appeals to our particular sense of humor

Why is it Hard for a Chatbot to Author Jokes?

  • It can be difficult for a chatbot to author jokes because humor is a complex and nuanced aspect of human communication. One reason is that humor often relies on context, shared knowledge, and cultural references that can be difficult for a machine to understand and replicate Artificial Intelligence Can Now Craft Original Jokes—And That’s No Laughing Matter | Corinne Purtill
  • Here are some of the laughter-related things that AI can't do. ChatGPT Can Craft Jokes, But Can AI Make Us Laugh? | Bob Sharp - Make Use Of
    • Contextual Understanding: Humor isn't just a joke with an attached punchline. There is more subtlety to humor than just this. There are cultural references, sarcasm as a humor tool, and humor that relies on subtleties of language. All these play a large part in what we consider humor. Unfortunately, AI models to generate humor are still lacking.
    • Lack of Emotional Understanding: Humor plays on our emotions. Of course, the end result should be laughter, or it wouldn't be humor. But the road to that laughter can play on many human emotions. This is a subtlety that AI can't factor into its humor and jokes.
    • Timing: Timing is one of those things that is hard to teach. It is a feeling; it is judging when the perfect time to reveal that killer punchline has been reached. AI models cannot factor in timing when creating comedy.
  • Your Wit Is My Command: Building AIs With a Sense of Humor | Tony Veale ... provides a computational roadmap for how we might get there.
    • Explanations are to jokes what autopsies are to bodies: if the subject isn’t already dead, it soon will be.
    • Shows that computers can be built with a sense of humor, capable not only of producing a joke but also of appreciating one.
    • In order for robots to be funny we need to analyze humor computationally. Using artificial intelligence (AI), Veale shows that joke generation is a knowledge-based process--a sense of humor is blend of wit and wisdom.
    • Existing technologies can detect sarcasm in conversation
    • Explains how some jokes can be pre-scripted while others are generated algorithmically
    • There is no single algorithm or technology that we can plug in to make our virtual assistants or GPS voice navigation funny



Can ChatGPT Write a Late-Night Monologue??

  • AI Fallon: " Okay, here goes: Why did the chicken cross the playground? To get to the other slide! See, that's the kind of classic, timeless humour that only a human brain can come up with. Well, that and maybe a five-year-old's brain, but you get the idea."
  • AI Colbert: "Big news today, folks! President Biden has announced that he will be running for re-election. That's right, the man who once said he didn't want to run for president because of his age is now saying, 'Age is just a number, and so is 78!' "Now, I know some of you might be concerned about President Biden's age. In a recent poll, 50% of Americans said they were worried about his age, and the other 50% were Joe Biden. But let's be real, folks, Biden's age is not a big deal. He's got the energy of a 30-year-old, and the memory of a... well, I forget what I was going to say."

AI Humor Research

YouTube ... Quora ...Google search ...Google News ...Bing News

AI humor research is an interdisciplinary field that combines techniques from artificial intelligence, cognitive science, linguistics, and psychology. Researchers have trained artificial intelligence to make jokes, but the advances are making many people uncomfortable. There are several methods for generating humor in AI, including using wordplay, irony, sarcasm, and satire. Computational humor is a branch of AI that deals with the generation and recognition of humor. In a study, algorithms accurately picked the jokes that people deemed funniest 61 percent of the time, whereas humans were correct 57 percent of the time. Scientists have developed an AI that appropriately detects and responds to human laughter at a shared moment during a conversation, which is another step toward creating more natural interactions between humans and robots. Some comedy writers see a need for artificial intelligence to master the art of levity, and they have used AI tools to build joke chatbots. Humor is one of those fundamental human qualities that we think of as being special for us as a species, especially when it comes to the contrast between us and machines. If you understand someone’s sense of humor, you understand them.

Conversational AI is focused on providing a specific response to what a person needs, but when we are joking with an AI agent, the agent needs to distinguish that we don’t have an intention to receive the real reply. The detection of humor can be solved by a mixed approach of machine learning and human insight. Some comedy writers see a need for artificial intelligence to master the art of levity, and they have used AI tools to build joke chatbots. However, the originality of AI-generated humor is lacking, and relying solely on AI may not yield the desired results for marketers looking to engage their audience through nuanced humor.

Incentivizing Language Models to find Humor

Researchers are exploring various approaches to improve AI's capabilities in generating humor, as cracking the code of machine-generated humor remains an open challenge. One promising avenue is leveraging game theory and the generator-discriminator framework to incentivize language models to generate more humorous and contextually appropriate jokes.

The Generator-Discriminator Framework The generator-discriminator framework is a key strategy in the pursuit of AI-generated humor. The generator component is responsible for creating potential jokes in response to a given context or prompt. Meanwhile, the discriminator acts as a critic, evaluating the jokes' quality and humorousness based on set criteria.

Generator The generator component generates potential joke candidates given some context or prompt. It proposes open-ended joke responses, drawing from its training data and language understanding capabilities.

Discriminator The discriminator component evaluates the quality and humorousness of the generator's jokes. It acts as a critic, scoring the jokes based on various criteria, such as:

  • Contextual relevance: Does the joke make sense given the prompt or context?
  • Incongruity and surprise: Does the joke contain an unexpected twist or punchline that creates a humorous incongruity?
  • Structural coherence: Is the joke well-formed and follows a logical setup-punchline structure?
  • Cultural and linguistic appropriateness: Is the joke respectful and appropriate for the target audience?

The generator and discriminator components can be trained in a game-theoretic setting, where they receive rewards or penalties based on their ability to generate and identify humorous jokes that satisfy the defined criteria

Leveraging Game Theory Game theory principles can be applied to incentivize the generator and discriminator to collaborate and improve their performance. For example:

  • The generator can be rewarded for generating jokes that the discriminator deems humorous and contextually appropriate.
  • The discriminator can be rewarded for accurately identifying humorous jokes and providing constructive feedback to the generator.
  • Both components can be penalized for deviating too far from their initial beliefs or knowledge about what constitutes a good joke.

By iterating through numerous rounds of this game, the generator and discriminator can learn from each other and refine their strategies, potentially leading to more sophisticated and humorous joke generation capabilities.

Challenges and Opportunities While the generator-discriminator framework and game theory principles show promise, cracking the code of machine-generated humor remains an open challenge. Some view AI's current limitations with humor as an opportunity to use it as an "infinite idea generator" to assist human comedians and writers in brainstorming humorous concepts, rather than fully automating joke creation. Researchers are also exploring other approaches, such as incorporating incongruity detection, understanding cultural contexts, and leveraging multi-modal inputs (e.g., images, videos) to enhance AI's humor capabilities.


Witscript

Witscript, a joke–generation system trained on a data set of TV–monologue jokes that detects keywords in entered text and creates a relevant punch line. Witscript is a neural-symbolic hybrid system based on algorithms that people use to write jokes. Unlike other forms of robot comedy, the system—which Toplyn has patented—can generate contextually relevant jokes on the spot in response to a user’s text. A chatbot or voice assistant enabled with the software can respond with humor to users’ queries (when appropriate) without derailing the interaction. Toplyn sees Witscript as an extension of the work he did for decades in late-night TV: making people laugh, and therefore making them feel less alone. “That’s basically the goal,” Toplyn says. “It’s to make chatbots more humanlike, so people will be less lonely.” In 2014 Toplyn published Comedy Writing for Late-Night TV: How to Write Monologue Jokes, Desk Pieces, Sketches, Parodies, Audience Pieces, Remotes, and Other Short-Form Comedy. The book is a distillation of a course he taught in New York City after scrutinizing decades of monologues and reverse engineering the most successful jokes. Toplyn isn’t precious about comedy writing: it’s a job, one that a person can learn to do well if given the right inputs. The jokes that got the biggest laughs for Leno and Letterman follow identifiable formulas populated with “handles”—people, places, things and other references—each with a variety of related associations that can be combined to form a punch line. Given enough time and data, he realized, a computer could potentially learn to make these jokes too. Artificial Intelligence Can Now Craft Original Jokes—And That’s No Laughing Matter | Corinne Purtill


Witscript - Prompt Chain

  1. Get a topic. Witscript 3 receives a sentence from a user and treats it as the topic of a three-part joke that consists of a topic, an angle, and a punch line. For example, a user might say to Witscript 3, "Authorities caught two pigs that were wandering around loose in San Antonio, Texas."
  2. Select two topic handles. The GPT-3 API is called with a prompt to select the two most conspicuous nouns, noun phrases, or named entities in the topic. That's because the humor of human-written jokes tends to be based on nouns and noun phrases (West and Horvitz 2019). From that example topic, GPT-3 selects the topic handles "pigs" and "San Antonio."
  3. Generate associations of the two topic handles. The GPT-3 API is called with a prompt to generate a list of associations for each topic handle. In our example, for "pigs" GPT-3 generates a list including bacon, pork chops, ham, and sausage. For "San Antonio" it generates a list including The Alamo, River Walk, Texas Longhorns, and Whataburger.
  4. Create three punch line candidates. Witscript 3 links associations of the topic handles in three different ways to create three punch line candidates: a wordplay candidate, a common-sense knowledge candidate, and a third candidate. To create its wordplay candidate, Witscript 3, like Witscript, uses well-known tools of natural language processing to combine one association from each list into a punch line that exhibits wordplay (Toplyn 2020). Witscript 3 does not call on GPT-3 to create its wordplay candidate because GPT-3 seems to be weak at phonetic tasks like generating puns and rhymes, possibly as a result of its use of byte-pair encoding (Branwen 2020). To create its common-sense knowledge candidate, Witscript 3, like Witscript 2, uses GPT-3 to combine one association from each list using common-sense knowledge. In our example, when the GPT-3 API is called, GPT-3 combines the associations "sausage" and "The Alamo" into the punch line "Alamo Sausage." Finally, to create its third candidate, Witscript 3 uses GPT-3 to power a third, proprietary, joke production mechanism involving the topic handles.
  5. Generate an angle between the topic and each candidate punch line. The GPT-3 API is called with prompts to generate three joke candidates, each one based on the topic and ending with one of the punch line candidates.
  6. Output the joke candidate that is most likely the funniest. The GPT-3 API is called with a prompt to determine which of the three joke candidates seems to be the funniest. Then Witscript 3 outputs that joke to the user as its response. In our example, after the user says, "Authorities caught two pigs that were wandering around loose in San Antonio, Texas," Witscript 3 outputs the response, "They were taken to the Alamo Sausage Company."

Jon

Don’t you hate it,” says Jon the Robot, gesturing with tiny articulated arms at an expectant crowd, “when you’re trying to solve inverse kinematics equations to pick up a cup and then you get ‘Error 453, no solution found’?” The crowd laughs. “Don’t you hate that?” An experiment billed as a comedy act, Jon is the brainchild of Naomi Fitter, an assistant professor in the School of Mechanical, Industrial and Manufacturing Engineering at Oregon State University. The tiny android performs when a handler (who must also hold the mic) presses a button, then tells the same jokes in the same order, like a grizzled veteran comic at a down-market Vegas casino. But the robot’s act is more human than it might first appear. Jon is learning how to respond to its audience—it can now vary the timing of its delivery based on the length of the audience’s laughter, and append different responses to jokes based on the level of noise in the room. It can deliver one line if a joke gets a roar of laughter (“Please tell the booking agents how funny that joke was”) and another if there are crickets (“Sorry about that. I think I got caught in a loop. Please tell the booking agents that you like me … that you like me … that you like me”). Artificial Intelligence Can Now Craft Original Jokes—And That’s No Laughing Matter | Corinne Purtill


Improbotics

An improv troupe that works alongside an AI that tosses out prompts and lines that human performers have to work into the show. Piotr Mirowski was working as a search engineer at Bing when he noticed the similarities between his day job and his personal passion, improv. The principle of search engineering is to teach the computer how to identify the best result for a given query. In improv, Mirowski says, performers are also trained to follow their instincts and do what feels best in that scene. It’s not always perfect, and the results sometimes have a hilarious absurdity, as anyone who has started typing a Google query with the predictive search feature on knows. Improv comedians often draw upon cues shouted out from the audience. An AI can draw upon ideas from all over the world and across history. The goal isn’t to build a thing that will make the laughs for us, Mirowski says, but instead one that can help humans find new things to laugh about. As with any new technology, its power will come from the way users choose to interact with it, with results that no one may yet have imagined. “I see what we’re doing as kind of like building the electric guitar. It’s not very clear how to play it or what it’s going to do, and it sounds really weird and distorted and there are enough acoustic guitars anyway,” says Kory Mathewson, Improbotics co-founder and cast member and a Montreal-based research scientist with DeepMind. “Then Jimi Hendrix gets an electric guitar, and it’s like, ‘Oh. That’s what this is about.’” Artificial Intelligence Can Now Craft Original Jokes—And That’s No Laughing Matter | Corinne Purtill


Improbotics' goal isn’t to build a thing that will make the laughs for us but instead one that can help humans find new things to laugh about. - Piotr Mirowski


HumorTools

HumorTools introduces twenty microtasks for joke creation. The microtasks are organized into seven major types:

  1. Aspect (1 microtask) Given a headline, identify its individual components. This may include people, things, actions or justifications for those actions.
  2. Expected Reactions (1 microtask) Given an aspect, describe your reactions to it, in or out of context. Reactions can bad positive or negative. Positive reactions include: an aspect is good or normal, deserves praise, or will succeed. Negative reaction include: an aspect is bad or weird, deserves blame, or will fail. By describing your reactions, you will probably be describing other peoples' expected reactions.
  3. Expected Reasons (1 microtask) Given an aspect and a reaction, provide a reason for that reaction. This brings detail and clarity to our instinctual reactions and finds truths deeper than surface-level reactions.
  4. Associations ( 6 microtasks) Given an aspect, name an associated aspect.
  5. Expectation Violation Mechanisms (2 microtasks) There are two types of expectation violation mechanisms: Sarcasm and Angle. Sarcasm is when you are given an expected reaction and expected reason that seem bad or false, you name a opposite reaction and belief that is exaggerated enough to indicate you are being sarcastic. Angle is when you are given an alternative belief or association, you name a belief that is contrary to an expected belief.
  6. Beliefs (8 microtasks) Given an expectation violation mechanism, a belief is an expression of the mechanism.
  7. Evaluation (1 microtask) Given a joke, check that it has the minimum requirement to be a joke: two connections, a violation mechanism and an unexpected belief

AI Humor Research ...continued

The latest examples of AI research into comedy demonstrate a growing ecosystem of tools, platforms, and applications that leverage AI's capabilities to generate and enhance humor. From specialized joke generators to AI-generated comedy specials, the field is rapidly evolving, with implications for entertainment, social media, and human-AI interactions. While AI's understanding of humor remains a work in progress, its role as a creative assistant and idea generator for human comedians is increasingly recognized. Ethical considerations and the importance of trust in AI-generated content are also critical aspects of this research area.

  • PFFT.AI is recognized as the first AI comedy tool designed to generate humorous content by merging the user's original ideas with the AI's humorous perspectives, PFFT.AI creates a blend of humor that is both fresh and entertaining. It's a space where human wit meets AI efficiency, offering a new and interactive approach to comedy creation.
  • Taskade AI Comedian Persona Generator offers a comedian persona generator, allowing users to create customized comedic characters - expanding its importance by being applicable not only to stand-up comedians, but also writers, content creators, and all those who want to amplify the humor and creativity in their work. Users can also tailor this dynamic tool according to their needs and use it on-the-go, which makes it all the more versatile. This means users can generate, edit, share, and download their comic personas at any time and anywhere, opening up a wide range of opportunities for comedic undertakings.
  • Punchlines.ai focuses on creating punchlines, a critical element of joke structure. punchlines.ai is an AI joke generation tool built on top of a large language model (LLM). It was fine-tuned on thousands of late night comedy monologue jokes.
  • MemeDaddy is an AI tool that generates memes, combining text and images for comedic effect
  • Meme-Yourself allows users to insert themselves into memes, personalizing humor
  • The AI Comedy Club on GitHub is a platform for developers and comedians to collaborate on AI-generated comedy. The stage is open only for AI performers! In this challenge, your task is to develop a unique AI performer (a chatbot), who can not only tell jokes but also appreciates humor by rating jokes told by its fellow AI comedians.
  • TeamSmart AI Comedian is tailored for generating humor in a corporate environment, potentially for use in presentations and team-building activities
  • SASI – Semi-supervised Algorithm for Sarcasm Identification … this machine algorithm, developed by an Israeli research team, was designed to assist AI with the recognition of sarcasm. They current report a 77% success rate and see no reasons why they cannot improve upon these results. Scientists are discovering that the detection of sarcasm is a very important and useful tool for humans and would certainly be a great advancement in AI technology.
  • STAND-UP – System To Augment Non-speaking Dialogue Using Puns; This program was created by a team of researchers in Scotland to assist children that use computerized speech aids to help them with certain communication challenges.
  • DEviaNT – Double Endendre via Noun Structure … the software that tells dirty jokes. Developed by two computer scientists in Washington University to determine appropriate word triggers or phrases that can be followed with ‘That’s what she said’ lines and apparently working with 70% accuracy.
  • Google’s natural language AI, PaLM (Pathways Language Model), is now able to understand jokes. The ability to understand the nuances of human language will lead to better and more natural interactions with machines No Joke: Google's AI Is Smart Enough to Understand Your Humor | Imad Khan - CNET ... Martin Wattenberg
  • Researchers have trained an artificial intelligence algorithm to understand and predict visual humor, representing a major development towards creating “common sense” machines Artificial Intelligence Algorithm Taught to Recognize Humor - Newsweek
  • Researchers at Kyoto University have developed an AI that appropriately detects and responds to human laughter at a shared moment during a conversation. This shared-laughter model is another step toward creating more natural interactions between humans and robots Sharing a laugh: Scientists teach a robot when to have a sense of humor | Peter Rejcek - Frontiers Science News
  • Use of AI to understand and generate humor. Research focuses on developing AI systems that can understand the meaning of jokes, generate new jokes that are both funny and relevant to the context in which they are being told, and write funny stories. | Michael H. Yeomans - Harvard Business School
    • Yeomans, M. H., & Jurafsky, D. (2019). A neural network model of humor. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 4306-4316).
    • Yeomans, M. H., & Jurafsky, D. (2020). A large language model for generating humorous text. In Proceedings of the Association for Computational Linguistics (ACL) (pp. 5316-5326).
    • Yeomans, M. H., & Jurafsky, D. (2021). Generating funny stories with a large language model. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 4297-4306).
  • Researchers at Stanford have made progress in developing AI systems that can generate humor. One approach is to use machine learning to train AI systems on large datasets of jokes and other humorous content. This allows the AI systems to learn the patterns and features that are common in humor. Projects on humor detection, sarcasm recognition, and joke generation. | William W. Cohen, Jurafsky & Juergen van Gael - Stanford University
  • Interested in the use of AI to understand and generate human language, including humor. | Oren Etzioni - CEO of the Allen Institute for Artificial Intelligence
  • Computational humor and developed algorithms for generating jokes and puns. | Anton Nijholt
  • Explored humor generation in AI systems. Some of their work involves developing models that can understand and generate puns. | University of Washington: The Computational Linguistics and Artificial Intelligence Lab
  • Studied computational humor and worked on projects involving humor recognition, generation, and evaluation. | Heriot-Watt University: Interaction Lab Scotland
  • Developing computational models of humor and has investigated various aspects of humor understanding and generation. | Virginia Tech: The Computational Synthesis Laboratory
  • Involved in humor research, including the development of computational models for generating puns and jokes. | University of Edinburgh: The Institute for Language, Cognition, and Computation
  • Interdisciplinary research on humor. They investigate computational approaches to humor generation and understanding, incorporating linguistic, psychological, and computational perspectives. | Humor Research Lab (HuRL): University of Colorado Boulder
  • Conducted research on computational models of social behavior, including the use of humor in human-computer interaction. | Justine Cassell: Carnegie Mellon University
  • Promotes research on computational creativity, which includes humor generation. They organize conferences and workshops where researchers present their work in this area. | he Association for Computational Creativity (ACC)
  • Conducted studies on computational humor and developed AI systems capable of generating jokes. IBM Research

Asking ChatGPT To Write Standup Comedy

  • The speaker, Josh, is testing whether ChatGPT can write funnier jokes than humans.
  • Initially, the AI's jokes are not funny, but it understands basic dialogue structure.
  • After several attempts, the AI generates a joke involving a cheating politician, which Josh finds amusing.
  • Josh realizes that the AI is more helpful for generating lists of things, as it can provide exhaustive options.
  • The AI struggles with misdirection jokes and comparing different scenarios but excels at puns.
  • Josh concludes that ChatGPT is better for editing and inspiration rather than writing jokes from scratch.

The First Stand-Up Comedy Special Written Entirely By Bots REACTION

  • The video explores the first stand-up comedy special written entirely by bots.
  • The special is poorly animated and features a comedian named Nissan.
  • The AI-written script includes jokes about dentists, the economy, cancel culture, and microwave impressions.
  • The AI also makes a pun with "propcorn" and jokes about Florida and dinosaurs.
  • The comedy special ends with a full circle moment involving a flag and a marriage certificate.

Media

Artificial Intelligence: Last Week Tonight with John Oliver (HBO)
Artificial intelligence is increasingly becoming part of our lives, from self-driving cars to ChatGPT. John Oliver discusses how AI works, where it might be heading next, and, of course, why it hates the bus.

Introducing Google Nose
We're excited to announce our newest addition to Search: Google Nose. What do wet dogs smell like? Google Nose! How about victory? Google Nose! Try searching on Google for "wet dog" and explore other smells that people sniffed for, or visit google.com/nose to learn more. Happy smelling!

Amazon Echo - SNL
The Amazon Echo Silver is specifically designed for the greatest generation (Kenan Thompson, Kate McKinnon, Leslie Jones, Kyle Mooney, Aidy Bryant).

LOL-BOT - THE WORLD’S FIRST A.I. COMEDIAN
This year, the Melbourne International Comedy Festival is unveiling the world’s first A.I. comedian, aptly named, LOL-BOT. Developed locally in Melbourne, LOL-BOT is a comedy-tech prototype that can generate its own on-the-spot jokes and pick up on real-time human reactions. He’s a shining example of the huge strides that are being made in artificial intelligence, albeit for a more humorous purpose.

COG Ai - Generative AI for Game Reviews
The software development team that built The Game Crafter, Component Studio, and Tabletop Events is excited to announce their newest project in the artificial intelligence space. Introducing COG Ai - Generative AI for Game Reviews.

Artificial Intelligence: Last Week Tonight with John Oliver (HBO)
Artificial intelligence is increasingly becoming part of our lives, from self-driving cars to ChatGPT. John Oliver discusses how AI works, where it might be heading next, and, of course, why it hates the bus.

Retrieved from "https://primo.ai/index.php?title=Humor&oldid=37260"