←Search results

Search “DeepSeek”

By relevance · Total 1346 results Clear search

Saturday

  2. cnBeta

    Claude web and desktop now offer a Chinese interface, but mainland China is still not on the list of supported regions

    Claude web and desktop have added a language selector, and the interface now supports Chinese (Simplified) and Chinese (Traditional), among more than thirty languages; the mobile app has not yet followed suit. In the billing country drop-down menu on the checkout page, China appears, and both the $20 Pro and $200 Max plans are selectable, but the official list of supported regions still does not include mainland China, Hong Kong, or Macao. Anthropic has previously imposed account bans and identity verification restrictions on access from unsupported regions; this Chinese interface is mainly aimed at overseas Chinese users.

    Claude web and desktop have added a language selector, and the interface now supports Chinese (Simplified) and Chinese (Traditional), among more than thirty languages; the mobile app has not yet followed suit. In the billing country drop-down menu on the checkout page, China appears, and both the $20 Pro and $200 Max plans are selectable, but the official list of supported regions still does not include mainland China, Hong Kong, or Macao. Anthropic has previously imposed account bans and identi

    Matched fieldsBody

    #hot-signal#Product updates#Anthropic

Friday

  2. Fortune Tech

    The Death of Humanity: Why AI Doom Theories Don't Hold Up

    Collective[i] co-founder Stephen Messer wrote an article rebutting AI doomsday theories, pointing out that the AI revolution has been underway for thirteen years and large language models have been widely adopted for three years, yet the U.S. unemployment rate remained in the 4.3% to 4.5% range from 2025 through the first three quarters of 2026. He cited a March 2026 paper by Anthropic economists and Danish data covering 25,000 employees and 7,000 enterprises, saying no rise in unemployment was found in jobs highly exposed to AI. He believes doomsayers shifted from job threats to AGI existential risks because dangerous narratives make them appear important.

    Collective[i] co-founder Stephen Messer wrote an article rebutting AI doomsday theories, pointing out that the AI revolution has been underway for thirteen years and large language models have been widely adopted for three years, yet the U.S. unemployment rate remained in the 4.3% to 4.5% range from 2025 through the first three quarters of 2026. He cited a March 2026 paper by Anthropic economists and Danish data covering 25,000 employees and 7,000 enterprises, saying no rise in unemployment was

    Matched fieldsBody

    #hot-signal#English text is being prepared.#Safety / alignment#Industry news
  3. heise onlineSelected

    Meta Releases 816B Open-Source Model Muse Spark Open, Partnering with Apple for Local Execution

    Meta has released the open-weight model Muse Spark Open, which uses a MoE architecture with 256 experts, activates about 42B parameters per token, has a context window of 1 million tokens, and supports text, image, video, and audio input but outputs text only. Meta has partnered with Apple to run the approximately 530 GByte four-bit quantized version on two interconnected Mac Studio M5 Ultra machines, distributing computation via the MLX framework and Thunderbolt 5, achieving about 25 output tokens/second at an 8192-token context. Artificial Analysis tests show that it scores 39 on the Intelligence Index, making it the strongest American open-weight model currently available, but it trails MiMo-V2.6-Pro's 46 points and GLM-5.3's 45 points, and ranks last in four Agent tests. The model weights are available on Hugging Face in two versions: 16-bit at approximately 1.6 TByte and four-bit at approximately 530 GByte, with API pricing at $1.25 per million input tokens and $4.25 per million output tokens.

    Meta has released the open-weight model Muse Spark Open, which uses a MoE architecture with 256 experts, activates about 42B parameters per token, has a context window of 1 million tokens, and supports text, image, video, and audio input but outputs text only. Meta has partnered with Apple to run the approximately 530 GByte four-bit quantized version on two interconnected Mac Studio M5 Ultra machines, distributing computation via the MLX framework and Thunderbolt 5, achieving about 25 output tok

    Matched fieldsBody

    #hot-signal#Model releases#Open-source ecosystem#Agents
  9. Hugging FaceSelected

    Hugging Face Releases Beam: A 501B Open Source Model Supporting 1M Context and Self-Hosting

    Hugging Face has released Beam, a 501B-parameter sparse MoE open source model aimed at long-text reasoning and agent tasks with 1M context, activating only about 23B parameters per token. The model uses 52 layers of hybrid attention, with 43 layers using a 512-token sliding window and 9 layers using global attention; the KV cache grows by 36 KiB per token, about one-sixth that of a full-attention approach. The official release provides three checkpoints—BF16, FP8, and NVFP4; NVFP4 can compress the weights from about 1 TB to about 280 GB, and day-0 support is already available in transformers, vLLM, and SGLang.

    Hugging Face has released Beam, a 501B-parameter sparse MoE open source model aimed at long-text reasoning and agent tasks with 1M context, activating only about 23B parameters per token. The model uses 52 layers of hybrid attention, with 43 layers using a 512-token sliding window and 9 layers using global attention; the KV cache grows by 36 KiB per token, about one-sixth that of a full-attention approach. The official release provides three checkpoints—BF16, FP8, and NVFP4; NVFP4 can compress t

    Matched fieldsBody

    #lab#Industry news#Open-source ecosystem#Hugging Face
  10. Artificial Analysis full articleSelected

    Reflection Releases Its First Model Beam, Scoring 30 on the Artificial Analysis Intelligence Index

    Reflection has released its first model, Beam, an open-weight model with 501B total parameters and 23B activated parameters. It scores 30 on the Artificial Analysis Intelligence Index, ranking second among US open-weight models, behind only Meta's Muse Spark Open (39) and ahead of NVIDIA's Nemotron 3.5 Super VL (26). Beam consumes about 26k output tokens per Intelligence Index task, of which about 19k are used for reasoning and 7k for answering; it scores 48.5% on AutomationBench-AA, but only 3.0% on Terminal-Bench 4.0. On AA-Omniscience, it answers 33% of questions correctly, with a hallucination rate of 47% and a net index score of 1.5.

    Reflection has released its first model, Beam, an open-weight model with 501B total parameters and 23B activated parameters. It scores 30 on the Artificial Analysis Intelligence Index, ranking second among US open-weight models, behind only Meta's Muse Spark Open (39) and ahead of NVIDIA's Nemotron 3.5 Super VL (26). Beam consumes about 26k output tokens per Intelligence Index task, of which about 19k are used for reasoning and 7k for answering; it scores 48.5% on AutomationBench-AA, but only 3.

    Matched fieldsBody

    #company#Model releases#Open-source ecosystem#Evaluations / benchmarks

Thursday