Introducing Hy4 Preview
- ID
- 19512
- Status
- summarized
- Published
- 30 Aug 2026, 7:53 AM
- Fetched
- 31 Aug 2026, 8:48 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Aug/29/hy4/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 6.5
- Created
- 31 Aug 2026, 8:48 AM
- Tags
- Audience
- developersai-ml-learnersai-agent-users
What happened
Tencent released Hy4 Preview, an open-weight text-only LLM with 770B total parameters (49B active) and a 1M token context window, a significant jump from July's Hy3 (295B total, 21B active, 256K context). Simon Willison notes the model's chat template reveals only two reasoning modes: 'high' (default) and 'no_think', and observes that its reasoning traces use deliberately imperfect English, likely for token efficiency.
Why it matters
If you build with LLMs via OpenRouter, Hy4 Preview is available now for experimentation — the 1M context window and explicit reasoning toggle ('high' vs 'no_think') are concrete knobs worth testing for long-context agent workflows. The open-weight release also means self-hosting is on the table once weights stabilize, relevant for teams weighing dependency on closed APIs.
Discussion angle
Compare Hy4's binary reasoning toggle ('high'/'no_think') against Qwen 3.8's overthinking problem Willison flagged earlier this month — does a simpler on/off switch actually produce better cost/quality tradeoffs than graduated reasoning effort?