Qwen3.8-LiveTranslate: Qwen's New Real-Time Simultaneous Interpretation Model
Qwen announced Qwen3.8-LiveTranslate, a next-generation real-time simultaneous interpretation model built on an Interleave architecture to improve faithfulness,…
Qwen announced Qwen3.8-LiveTranslate, a next-generation real-time simultaneous interpretation model built on an Interleave architecture to improve faithfulness,…
Qwen has unveiled Qwen3.8-LiveTranslate, a next-generation real-time simultaneous interpretation model built on an Interleave architecture to improve translatio…
Qwen announced Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on an Interleave architecture. It cuts average lagging (LAAL) from 2.8…
Command Code says it achieves 197 tok/s median effective throughput on DeepSeek V4.1 Flash, topping three other routes by up to 2.6x in a real-call benchmark.
LiteLLM now supports Jev, a model/agent from TypeSafe AI. Developers are already using it, including LiteLLM internally. A highlighted use case: a Jev-powered P…
GLM-5.3 FlashX, a high-speed variant of GLM-5.3 Flash, is now live in Command Code with ~200 TPS, a 1M context window, and multimodal support.
Muse for Mac now features built-in instant voice dictation: hold the fn key and start talking, with no separate dictation app or setup required.
Muse, a personal AI agent, is opening developer access to build connectors that link third-party services into the agent. New connectors are live today, with Gr…
Muse, a personal AI agent, has announced a Notion integration, allowing it to find context, make updates, and keep work moving directly from your Notion docs.
Muse announced that developers can now build custom connectors: bring your own API and Muse supplies the agent, browser, and user context.