Study Reveals Large Language Model’s Limitations in Humor; ChatGPT Struggles to Be the Life of the Party

“Can machines be funny?” That’s a question that has been asked by many researchers exploring the field of computational humor. A recent study by researchers at Stanford University and Google Research set out to find the answer, taking a look at the humor-generating capabilities of ChatGPT, one of the largest language models in the world.

ChatGPT is part of the GPT family of language models that forms the backbone of the OpenAI language model. This model has learned to generate text that bears remarkable similarities to human writing. The study aimed to explore whether ChatGPT could generate funny content like a human.

The researchers tested ChatGPT’s ability to create humor by presenting it with a joke prompt and analyzing the response. They discovered that more than 90% of the time, ChatGPT’s response was a repetition of one of the 25 different jokes provided.

The top four jokes were recycled in more than half of the responses. This result points to an issue highlighted in the study: while ChatGPT can generate a large amount of text, a significant proportion of that text is repetitive and predictable.

ChatGPT’s contribution

Despite these limitations, the study suggests that ChatGPT is a significant step in the direction of creating “funny” machines. Humor has always been seen as too subjective of a field to develop an algorithm that can effectively create it. However, the study shows that despite the limitations, ChatGPT can generate coherent jokes, demonstrating its potential in various natural language tasks.

The researchers also observed that ChatGPT displayed an understanding of wordplay and double meanings. This result suggests that future iterations of the program may lead to significant advancements in this area.

Difficulty confirming beyond training data

However, the study acknowledges that it is challenging to confirm whether the jokes were hard-coded without access to more extensive language model training data. Without expanding the dataset used in the study, it is difficult to say whether ChatGPT learned these jokes through training or whether these jokes were hard-coded into the algorithm.

ChatGPT’s Limitations

While ChatGPT shows potential for advancements in computational humor, the study concludes that the model cannot confidently create intentionally funny original content. ChatGPT can respond to prompts using its vast dataset of pre-existing jokes, but it still struggles to create original humor.

In other instances, the model struggled to make sense of the joke’s setup, which led to a lack of cohesion and became an obstacle to humor. However, it is worth noting that humor often relies on cultural and contextual understandings, which may be difficult for a language model to grasp.

The study highlights the difficulty for large language models to understand and create humor. As of today, machines are no match for human humor. Yet, the study concludes that even though ChatGPT cannot yet generate intentionally funny, original content, it represents a significant leap forward in the design of machines that have a sense of humor. The potential conveyed by ChatGPT could pave the way for subsequent studies that will analyze humor in more detail, bringing us closer to the day when machines will be able to make us laugh.

Explore more

Why Should Leaders Invest in Employee Career Growth?

In today’s fast-paced business landscape, a staggering statistic reveals the stakes of neglecting employee development: turnover costs the median S&P 500 company $480 million annually due to talent loss, underscoring a critical challenge for leaders. This immense financial burden highlights the urgent need to retain skilled individuals and maintain a competitive edge through strategic initiatives. Employee career growth, often overlooked

Making Time for Questions to Boost Workplace Curiosity

Introduction to Fostering Inquiry at Work Imagine a bustling office where deadlines loom large, meetings are packed with agendas, and every minute counts—yet no one dares to ask a clarifying question for fear of derailing the schedule. This scenario is all too common in modern workplaces, where the pressure to perform often overshadows the need for curiosity. Fostering an environment

Embedded Finance: From SaaS Promise to SME Practice

Imagine a small business owner managing daily operations through a single software platform, seamlessly handling not just inventory or customer relations but also payments, loans, and business accounts without ever stepping into a bank. This is the transformative vision of embedded finance, a trend that integrates financial services directly into vertical Software-as-a-Service (SaaS) platforms, turning them into indispensable tools for

DevOps Tools: Gateways to Major Cyberattacks Exposed

In the rapidly evolving digital ecosystem, DevOps tools have emerged as indispensable assets for organizations aiming to streamline software development and IT operations with unmatched efficiency, making them critical to modern business success. Platforms like GitHub, Jira, and Confluence enable seamless collaboration, allowing teams to manage code, track projects, and document workflows at an accelerated pace. However, this very integration

Trend Analysis: Agentic DevOps in Digital Transformation

In an era where digital transformation remains a critical yet elusive goal for countless enterprises, the frustration of stalled progress is palpable— over 70% of initiatives fail to meet expectations, costing billions annually in wasted resources and missed opportunities. This staggering reality underscores a persistent struggle to modernize IT infrastructure amid soaring costs and sluggish timelines. As companies grapple with