Tiny Army, Eyas win Build Small hackathon
Cohere co-sponsored Hugging Face's 'Build Small' hackathon, which challenged developers to create useful, whimsical, or cool applications using smaller, more efficient AI models. Two projects powered by Cohere's models received awards: 'Tiny Army,' an interactive game by @polats where players describe and create their own heroes, won second place on the Thousand-Token Wood track; and 'Eyas,' a security camera agent built by Hanhee Lee, Javier Huang, and Joe Lee to solve real-world security needs for a family convenience store, won the Best Agent award.
Hot Take: Building small is the new building big; developers are proving that resource-constrained, highly-targeted local AI agents can solve real-world problems more efficiently than bloated general-purpose models.
- –**Tinkerability over Scale:** The success of games like Tiny Army demonstrates that user engagement depends on creative implementation rather than massive parameter counts.
- –**Practical Application:** Eyas highlights a growing trend of bespoke, localized AI agents built to address specific, everyday business needs (e.g., convenience store security).
- –**Efficiency and Cost:** Leveraging smaller models like Cohere's allows for faster iteration, lower latency, and significantly reduced deployment costs, making custom AI accessible for individuals and small businesses.
DISCOVERED
3h ago
2026-07-13
PUBLISHED
3h ago
2026-07-13
RELEVANCE
AUTHOR
cohere