Tencent's Hy4 rebuilds 7M-cell embryo in 1.5h, trains self-improving models
heyshrutimishra · x · 2026-11-04
Tencent's Hy4 delivered multiple notable results: trained with developers from its games division on Unreal, Unity and Godot, the Honor of Kings team reports bug root-cause accuracy improved from 59.5% to 73.8%. It also rebuilt a 3D mouse embryo from 7 million cells in 1.5 hours on a single machine. Paired with the Hyra 2.0 harness, Hy4 trained a smaller model on its own that beat Tencent's official baseline on multiple benchmarks — groundwork for "recursive self-improvement". A single prompt also generated Tencent's Penguin Island campus as a 3D offline single-file HTML with first-person walking, weather and day/night.
More from Models
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04