Cohere Labs launches CulturalRiddles: 6.2k riddles from 45 countries that stump LLMs
cohere · x · 2026-10-22
Cohere Labs released CulturalRiddles, a new open-science benchmark measuring culture as intertwined, lived experience — revealing that LLMs acing math and science often fail at basic cultural riddles.
The project's backstory is unusual: it started with Hungarian diplomat Boczka Károly and grew to include contributors like high schooler Henry Gagnier and retired math teacher Jane Smith. Collaborators wrote original riddles about their own cultures in their own languages, yielding 6,200 riddles from 45 countries. According to Cohere, open science taught the people involved as much as the models.
More from Research
- CONCERT: Generative Modeling of Spatially Resolved Perturbation Responses — anshulkundaje · 2026-10-22
- ToM2Vec trained via self-play with Qwen3-8B transfers to GPT-5.4 teams, adding 17.3 points — EliasEskin · 2026-10-22
- ToM2Vec: continuous theory-of-mind vectors help LLM agents coordinate with unseen partners — EliasEskin · 2026-10-22
- Hands-on: building protein design workflows with RFD4-Proteina on Hugging Face Spaces — AllThingsApx · 2026-10-22
- edgePython v0.5.0 released: 4-6x faster than edgeR, camera over 100x speedup — lpachter · 2026-10-22
- 'Agentic Inequality' paper published in Nature Machine Intelligence: who captures AI's surplus agency — IasonGabriel · 2026-10-22