New Kimi model fine-tuned for game development and 3D
Kimi was fine-tuned for Unity, Unreal Engine, Godot and 3D generation, and demonstrated an autonomous walking-simulator case.
The Kimi model, according to the developers, was fine-tuned with a focus on game development and 3D. It reportedly works well with Unity, Unreal Engine and Godot, combining them with web search and 3D generation. It also performs reasonably well on longer-horizon tasks.
For example, the announcement includes a case where Kimi autonomously built a human walking simulator based on an anatomical model. The model created training pipelines on its own, tuned the reward function and physics, reviewed results and refined the step controller. Over 167 iterations and 420 independent reviews, the virtual human progressed from falling on the first step to continuous walking with alternating steps for 11 seconds.
It is not yet close to recursive self-improvement, but the skills needed for certain kinds of ML research are already visible.
Why it matters
AnalysisThe result shows AI models increasingly bridging game engines, 3D generation and autonomous ML workflows, pointing toward more capable simulation and research tooling.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Kimi K3.1 Launches as a 2.8T-Parameter AI Model
Kimi K3.1 is described as a very large open model with 2.8 trillion parameters and 104 billion active parameters, but its weights have not yet been released.
Kimi K3.1: teaser hints at new model from the Kimi team
The Kimi team published a teaser suggesting a fast arrival of Kimi K3.1, expected to be the best among available Chinese AI models and significantly cheaper than Kimi K3.
Autonomous AI Operator on Telegram 24/7: Architecture, Telethon, Security, and 10 Production Scenarios
A comprehensive engineering guide to building a production-ready AI operator on Telegram using Telethon: session isolation, confirmation systems, ban protection, and 24/7 deployment.
Loop Engineering: Architecture of Autonomous Agentic Loops and the Post-Prompting Era
A deep dive into Loop Engineering: self-sustaining execution loops for Claude Code and autonomous agents, the DOER/CHECKER topology, deterministic verification, the /goal primitive, and reward hacking mitigation.
Custom GPTs
ChatGPT's feature for creating personalized mini-assistants tailored to specific tasks. It allows uploading custom files, setting persistent instructions, integrating image generation, and connecting external APIs without coding.
Dynamic Tool Selection
An architectural approach for building scalable AI agents equipped with hundreds of tools. Instead of loading all function descriptions into the context simultaneously, the system employs semantic search or a Router model for dynamic selection of only 3-5 most relevant tools for a specific user query.