How Tencent HY4 Preview Performs in Coding Tests

Bijan Bowen35:25
1 VIEW
0 comments · 0 votesOpen discussion
Sign in to join the discussion

    Video summary

    Bijan Bowen reviews Tencent HY4 Preview as a 770-billion-parameter mixture-of-experts model with 49 billion active parameters, a one-million-token context window, Apache 2.0 weights and a built-in speculative-decoding layer. Tencent positions it for long-horizon software engineering and document-heavy work, while acknowledging that the preview can overthink and oververify tasks.

    The hands-on tests cover a browser operating system, a skateboard game, a subway shooter, an interactive watch page, a Blender city timeline and a retro wrestling game. HY4 often produces rich details, functional interactions and ambitious visual scenes, but several outputs need targeted fixes, omit requested behavior or show obvious preview-stage defects.

    Bowen's strongest criticism is the serving experience. Frequent 429 rate-limit errors interrupt long agentic runs even after he supplies billing details, making the hosted model unreliable for sustained work. He remains optimistic about the full release and a possible smaller variant, but treats the current preview as promising rather than production-ready. Subscription and comment requests are omitted.

    Original YouTube thumbnailWatch on YouTube