06-04, 16:30–17:10 (Europe/London), Warwick
This talk is about how advances in Large Language Models (LLMs) are helping make inroads into the 11 types of comedy. For many years most, but not all, types of humour were beyond the reach of automated systems. This talk is for those interested in comedy, how it is created, the state of the art in LLMs, and comedy datasets. This talk will include specific code examples as well as trying to be humorous in its own way. At the end the audience will have learnt how LLMs are changing the human/computer comedy landscape.
Objective of talk
To review the state of the art in comedy automation and machine assisted comedy, particularly as relates to recent developments in Large Language Models (LLMs)
Outline
- LLMs
- 11 types of comedy
- Comedy Automation
- Machine Assisted Comedy
- Comedy Datasets
- Progress on the 11 types
Central Thesis
Easy access to LLMs have changed what’s possible in terms of comedy automation and machine assisted comedy.
Key Takeaways
Human comedy is hard
But LLMs have adjusted the playing field
Background Knowledge assumed
General familiarity with Python and HuggingFace
No previous knowledge expected
