Blind Test of 48 LLM Jokes Shows AI Humor Is Improving

Paras Chopra ran an experiment where 62 participants blind-rated 48 jokes from six frontier models. Results and a two-year comparison show LLMs' sense of humor has steadily improved.

2026-10-06 ~ 2026-10-06 · 2 related posts

• 62-person blind test of 48 LLM jokes shows models are getting funnier, Astra tops with 50%+ laughs — paraschopra · 2026-10-06
• How funny are frontier AI models? Full methodology and the winning joke — paraschopra · 2026-10-06