Snipd home pageGet the app
public
Data Skeptic chevron_right

Evaluating Jokes with LLMs

whatshot 7 snips
Jun 6, 2023
Guest
Fabricio Goes
43:11
forum Ask episode
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
1
Introduction
00:00 • 2min
chevron_right
2
Computational Creativity: A Sub-Field of Artificial Intelligence
02:24 • 5min
chevron_right
3
How to Invent Your Own Recipes
07:14 • 2min
chevron_right
4
How to Interact With Non-Technical Creative Professionals on This Endeavor
08:48 • 4min
chevron_right
5
How Machine Learning Can Predict What Humans Will Like
12:40 • 4min
chevron_right
6
How GPT-4 Generates Poetry
16:32 • 4min
chevron_right
7
How to Evaluate the Quality of a Joke
20:13 • 4min
chevron_right
8
How to Create a Virtual Crowd Instead of Having One Kind of GPT
23:44 • 4min
chevron_right
9
How to Rate Jokes in GPT
27:47 • 4min
chevron_right
10
The Future of Generative Agents
32:02 • 3min
chevron_right
11
CrowdScore: The Future of Humor
35:23 • 2min
chevron_right
12
The Limits of Large Language Models
37:09 • 3min
chevron_right
13
The Future of Creativity
40:24 • 3min
chevron_right

Fabricio Goes, a Lecturer in Creative Computing at the University of Leicester, joins us today. Fabricio discussed what creativity entails and how to evaluate jokes with LLMs. He specifically shared the process of evaluating jokes with GPT-3 and GPT-4. He concluded with his thoughts on the future of LLMs for creative tasks.

HomeTop podcastsPopular guests