Portable agent memory from Tencent: the Hy4 preview squeezes 1.5 terabytes into 214 gigabytes

In the Hunyuan Hy4 preview, agent memory travels across Claude Code, DeepSeek Harness and WorkBuddy; a 1.5 TB memory shrank to 214 GB with almost no benchmark loss, running on a single 4090 laptop.

Paylaş
Portable agent memory from Tencent: the Hy4 preview squeezes 1.5 terabytes into 214 gigabytes

Tencent's AI team announced the Hunyuan Hy4 preview with an unusual emphasis: memory, over model. In the team's words, most teams ship an open model and call it done; what Hy4 brings is agent memory that travels across Claude Code, DeepSeek Harness and WorkBuddy. Instead of being locked into a single vendor's database, the memory moves with the agent.

The numbers land too: 1.5 terabytes of agent memory compressed to 214 gigabytes with almost no change on benchmarks, and the package runs on a single 4090 laptop or a box of four A4000s. On code, the Hy4 preview climbed to fifth on Code Arena's WebDev ranking; Hy3 sat at 31st two months ago. Virtual environments get attention as well: an agent can be paused on one machine and woken on another with its state intact. All of it open source.

The context is familiar: we covered Tencent's ContextPilot yesterday, which teaches context management to the model; Hy4 is the memory front of the same war. It also makes the lock-in debate of the agent era concrete: an agent that carries its memory in its pocket can move to any harness it likes, and what keeps the customer has to be the service itself, no longer the database.

Devamını oku

OpenAI تصنف أسترا أول نموذج «حرج» في الأمن السيبراني: ثغرتان غير معروفتين ووصول مقيد عند الإطلاق

OpenAI تصنف أسترا أول نموذج «حرج» في الأمن السيبراني: ثغرتان غير معروفتين ووصول مقيد عند الإطلاق

قالت OpenAI إن نموذج أسترا بلغ عتبة «الحرج» في الأمن السيبراني ضمن إطار الجاهزية بعد أن اكتشف ثغرتين غير معروفتين أثناء الاختبار؛ الإطلاق قريب، لكن القدرات المتقدمة ستُتاح لمجموعة محدودة أولاً.

GlobalFeed Editor tarafından