Published Jun 6, 2023

Evaluating Jokes with LLMs

Discover the fascinating intersection of AI and humor as Fabricio Goes delves into how large language models like GPT-3 and GPT-4 can evaluate jokes, potentially transforming creative processes with human-AI collaboration.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

LLMs for Evil
Answers 383 questions
I LLM and You Can Too
Answers 383 questions
Do LLMs Make Ethical Choices
Answers 383 questions
LLMs in Music Composition
Answers 383 questions
Emergent Deception in LLMs
Answers 383 questions
Deploying LLMs
Answers 383 questions
LLMs in Social Science
Answers 383 questions
Process Mining with LLMs
Answers 383 questions
Which Professions Are Threatened by LLMs
Answers 383 questions
LLMs for Data Analysis
Answers 383 questions
Program Aided Language Models
Answers 383 questions
ELMo
Answers 383 questions
Evaluating AI Abilities
Answers 383 questions
Trusting Machine Learning Models with LIME
Answers 383 questions
BLEU
Answers 383 questions

Dexa/Kyle Polich

Evaluating Jokes with LLMs

Topics covered

Popular Clips

Persona-Based Prompting

Creativity and LLMs

Evaluating Creativity

Creative Feedback Loop

Comedy and AI

Humor and AI

Evaluating Creativity

Machine Creativity Unleashed

Evaluating Humor with AI

Career Opportunities at Bloomberg

Generative Agents Exploration

Fine-Tuning Poetry

Future of Creativity

Episode Highlights

Humor and AI

Evaluating Creativity

Future of Creativity

Related Episodes

LLMs for Evil

I LLM and You Can Too

Do LLMs Make Ethical Choices

LLMs in Music Composition

Emergent Deception in LLMs

Deploying LLMs

LLMs in Social Science

Process Mining with LLMs

Which Professions Are Threatened by LLMs

LLMs for Data Analysis

Program Aided Language Models

ELMo

Evaluating AI Abilities

Trusting Machine Learning Models with LIME

BLEU

Evaluating Jokes with LLMs

Topics covered

Popular Clips

Episode Highlights

Humor and AIFabricio Goes explores the intersection of AI and humor, examining how large language models (LLMs) like GPT-3 and GPT-4 can evaluate jokes. His work highlights the potential for AI to assist in creative tasks by aligning machine evaluations with human humor assessments.

Humor and AI

Evaluating CreativityFabricio Goes explores the role of humans and AI in evaluating creativity, focusing on joke evaluation. He discusses the potential of AI, like GPT, to assist in creative tasks, while emphasizing the importance of human judgment.

Evaluating Creativity

Future of Creativity

Related Episodes