部分報道的翻譯與分析尚未完成，已標示來源內容。精選優先顯示處理完成的報道。
即時監測
即時追蹤可信來源，保留出處、權限和站內閱讀模式，把噪音壓成可讀情報。
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Featured RAGLLMUnstructured RAG Needed Mediocre Data. Agents Need Extraordinary Data. Oct 14, 2026 Featured RAGLLMUnstructured RAG Needed Mediocre Data. Agents Need Extraordinary Data. Oct 14, 2026 Authors Brian Raymond…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Key takeaways Teams of agents unlock a new axis of inference-time scaling. On challenging coding tasks, well-organized teams outperform single agents, with gains of up to ~10 percentage points on ProgramBench. But these…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI models Deploy Runway’s video models on Baseten You can now deploy Runway’s Gen-4.5 and Aleph 2.0 on secure, single-tenant environments on Baseten. Authors Albert Lee Published October 14, 2026 Share Published October…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI models Deploy Runway’s video models in dedicated environments on Baseten You can now deploy Runway’s Gen-4.5 and Aleph 2.0 on secure, single-tenant environments on Baseten. Authors Mike Bilodeau Albert Lee Published…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Anthropic opens Singapore office and signs MOU with the Government of Singapore Oct 14, 2026 Today, we are expanding our Asia-Pacific operations by opening a new office in Singapore—our fifth in the region—and signing a…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Oct 06 2026 MoE Math Demystified: What Does 8x7B Actually Mean? Daria SobolevaEtienne Goffinet MoE Fundamentals | Router Wars | Debugging Dead MoE Models | MoE at Scale | MoE Math Demystified This video breaks down MoE…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Oct 06 2026 MoE at Scale: Making Sparse Models Fast on Real Hardware Daria SobolevaQuentin Anthony MoE Fundamentals | Router Wars | Debugging Dead MoE Models | MoE at Scale | MoE Math Demystified In this video we discus…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI models Delivering real-time text-to-speech with Gradium Achieve natural-sounding conversational experiences using Gradium TTS on Baseten. Authors Albert Lee Published October 13, 2026 Share Published October 13, 2026…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Key takeaways Request shape matters more than request volume alone. A few large embedding requests can consume significantly more compute than thousands of small search queries. RPM alone is not a reliable sizing metric…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：News Project Beacon: Bringing safety signals to open models at scale Baseten partners with Goodfire AI to bring safety controls to open model inference. Authors Sai Maddali Published October 9, 2026 Share Published Octo…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Model performance What makes a high-quality NVFP4 quantization? NVFP4 makes models smaller and faster, but quantizing some layers can hurt quality. An intuitive look at how to choose which layers can run at 4 bits. Auth…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Introducing the Anthropic Cyber Mission Oct 8, 2026 Today we’re launching the Anthropic Cyber Mission, a long-term commitment to securing the systems everyone depends on. The Cyber Mission is a new effort to support def…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：2026 Usage Policy update Oct 8, 2026 Each year, Anthropic updates its Usage Policy in response to the evolving capabilities of our models, and the feedback we’ve received from our customers. We're publishing a new versi…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Building on our commitment to American scientific discovery Oct 8, 2026 Anthropic is deepening its support for American scientific research by committing $150 million over three years to the Genesis Mission, a federal i…
Anthropic 擴展 Cyber Verification Program，為經審核的安全專業人員設立三個訪問層級，併合並 Project Glasswing 與原 CVP。各層級在驗證要求、安全控制和攔截範圍上不同，目標是在監控濫用的同時，讓防禦方更廣泛地獲得先進網絡能力。
Cohere 的研究顯示，混合英語推理數據、多語言推理數據和多語言非推理數據，可讓模型在用户語言中推理。Tiny Aya L2-Thinker（3.35B）在 60 種語言中超過 93% 的情況下用提示語言思考，準確率損失很小，並在低資源語言上保持表現。研究還發布了模型權重與多語言推理數據。
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Featured File TransformationLLM How to Parse a Form Oct 5, 2026 Featured File TransformationLLM How to Parse a Form Oct 5, 2026 Authors Ajay Krishnan Dev Rel Engineer, Unstructured In this article Join our newsletter to…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：PwC and Cohere announced a global alliance, launching first in Canada, to help organizations deploy secure enterprise AI and turn AI investment into measurable business value. The alliance brings together North, Cohere’…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Key takeaways New agent harness: North 2 has a redesigned orchestration system enabling more sophisticated, reliable, multi-step automations and agents across the enterprise. Increased intelligence: Build smarter workfl…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI engineering Purpose-built LLMs for dental note-taking Frontier thinking model performance at a fraction of the latency. Authors Harry Partridge Charles O'Neill Last updated April 16, 2026 Share Dentists spend a surpr…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Model performance Agentic inference optimization: 50-90% faster engines Claude Code with Fable 5 built a Qwen 3.6 inference engine that beat vLLM by up to 90% on decode speed and 2.3x on TTFT, using MetaInfer skills on…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Anthropic invests $100 million to train 10,000 engineers and tackle the enterprise AI talent gap Oct 2, 2026 Learn more The first-of-its-kind Academy trains Frontier Deployed Engineers using the same standard of skills…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Research How we built the fastest GLM-5 on Artificial Analysis We achieved 200+ tokens per second on GLM-5. Authors Madison Kanna Tri Dao Philip Kiely Last updated October 2, 2026 Share TL;DR Using our low-overhead spec…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Reinforcement learning: Why alignment of numerics and MoE routing matter Join us for our inaugural conference, Forge 2026 Blog Reinforcement Learning Why Alignment Of Numerics And Moe Routing Matter Reinforcement learni…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：3 Higher accuracy across extraction tasks Long lists Records spanning pages Scanned forms Advanced Citations How we built v2.5 Try v2.5 on your documents Today we’re introducing Extract v2.5, a new generation of our sch…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Barclays scales Claude to upgrade operations and improve client experience Oct 1, 2026 Barclays, the British universal bank, is expanding its strategic collaboration with Anthropic to integrate secure, enterprise-grade…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Sep 30 2026 How AlphaSense Uses Fast Inference to Make Agentic Research Interactive Alec McLeanGriffin Marge Cerebras: Alec McLean and Griffin Marge AlphaSense: Chris Ackerson, Daniel Campos, Eldar Tinjic, Matt Lapointe…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：strong]:tw-font-normal tw-text-gray-600">Introducing Eleven v4Meet Eleven v4, our most emotive model yet. With 3x credits included on Creator+ until October 12 Discover Skip to content Log inSign up Contact salesLog in…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：How well does nDCG capture the quality of modern retrieval systems? nDCG is the established yardstick for measuring how well search systems rank results, and is widely used across benchmarks such as MTEB and BEIR. It is…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Key takeaways State-of-the-art enterprise retrieval: Embed 5 Pro achieves the highest average score of any model we tested - particularly across financial datasets, parsed PDFs, and visually rich documents. A new Fast t…