# Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor

> Полный текст доступен на английском

**Published:** 2 октября 2026 г.
**Author:** Sam Larson
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/comedic-fool-s-gold-reward-exploits-and-countermeasures-in-conversationa

We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches aim to capture understandable surprise and predicted audience amusement. Controlled tests show that an embedding-based surprise…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.00197)

**Теги:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*