Why hasn't any mainstream game integrated LLMs into NPCs yet?
Summary
Explores why mainstream games have not yet integrated large language models into NPCs, questioning whether latency issues or lack of interest from game studios are the primary obstacles.
Similar Articles
It's 2026...where are all the AI NPCs?
A retrospective analysis of why AI NPCs in games haven't taken off by 2026, citing prohibitive inference costs and lack of proven fun as key challenges, while exploring potential solutions like ground-up game design and local LLMs.
Why don't we still have any games with AI agents used as NPC characters?
The article questions why AI agents haven't been reliably integrated as NPC characters in video games, despite demonstrations like NVIDIA's AI-NPC from three years ago and the existence of capable open models like Gemma 4. It argues that the gaming industry's lack of effort in this area undermines claims about AI agent capabilities.
Why are large language models so terrible at video games?
An interview with Julian Togelius explores why large language models struggle with video games, citing game diversity, data scarcity, and lack of general game AI, while noting exceptions like Gemini beating Pokemon Blue with custom software.
@GuiveAssadi: AI Dungeon was the first LLM consumer product I am aware of. However, the use of LLMs to dynamically generate character…
A discussion noting that AI Dungeon was the first LLM consumer product, yet dynamic LLM character speech in games remains niche.
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
This paper argues that large language models struggle with causal reasoning and long-horizon planning due to a mismatch between sequence prediction and reasoning over latent environment dynamics, and introduces the Latent Dynamics Inference perspective along with the Flux environment to study these limitations.