Tencent releases Hy4, a powerful frontier AI model introducing visual understanding and computer use
Tencent’s Hy4 is a new large language model that uniquely combines visual understanding, reasoning, and tool‑calling to enable computer‑use capabilities for the first time. The model claims to deliver long‑horizon agentic performance, allowing it to interact with external tools and execute multi‑step tasks across modalities. Hy4’s architecture integrates a vision encoder with a language backbone and a dedicated tool‑calling interface, trading off increased inference latency for richer task execution. The announcement signals a step toward more autonomous, multimodal agents that can bridge perception and action in real‑world workflows.
⚡ Key Takeaways
- Hy4 is the first model announced by Tencent that supports
Want the full story? Read the original article.
Read on SiliconANGLE AI ↗