Skip to content
Live
#Engineering
  1. ITHome · AI72

    Cloudflare's open-source AI-powered browser Kitesurf has lower resource consumption than Chromium

    Cloudflare announced the open-sourcing of Kitesurf, its AI-powered browser launched in August this year, with the code released on GitHub. Kitesurf runs on Cloudflare Workers, completing HTML parsing, CSS application, executing page JavaScript, and screenshot rendering without a Chromium process or container, and supports the Chrome DevTools Protocol.

    Why it matters: Cloudflare has open-sourced a browser designed for agents and provides a resource comparison with Chromium, allowing readers to judge the deployment cost of high-concurrency agent tasks.

  2. Google Research88

    Google Opens /teamwork Multi-Agent Workflow in Antigravity

    Google has opened the /teamwork multi-agent workflow in Antigravity to external researchers and developers, which can be used in conjunction with Gemini 4 Argon, Carbon, and Hydrogen; /boost and Deep Review are also available.

    Why it matters: Google has disclosed /teamwork's specific results in multi-agent research and engineering tasks and made it available for external researchers to use.

  1. Hugging Face Blog65

    llama.cpp and ggml release v1.0.0, establishing semantic versioning rules.

    llama.cpp and ggml release v1.0.0, binding destructive changes to the public C API to the major version number, and both will be released according to semantic versioning rules thereafter. The project has supported over 150 model architectures and mainstream speculative decoding methods, and provides pre-release binaries for Linux, macOS, Windows, Android, iOS, as well as distribution channels such as Docker, Homebrew, and conda-forge.

    Why it matters: llama.cpp and ggml are released simultaneously with v1.0.0, and the major version number corresponds to destructive changes to the C API, allowing downstream dependents to plan their upgrade schedule accordingly.

  2. QbitAI80

    DeepSeek has opened the entire suite of application APIs, with voice interfaces included for the first time.

    DeepSeek has officially opened the entire suite of application APIs, including online search, deep thinking search, file upload, and link reading features within the app, all providing independent interfaces that can be called separately and billed individually. Voice capabilities have been included in the open list for the first time, including ASR and TTS interfaces. The original price for speech recognition is 0.78 yuan per hour, now half off at 0.39 yuan per hour, and speech synthesis is 1.5 yuan per 10,000 characters.

    Same story · 2 outlets

    Why it matters: The original text lists the tool interfaces opened by DeepSeek and the half-price voice pricing, allowing readers to estimate the call costs for voice assistant and document processing applications.

  3. vLLM Blog60

    vLLM supports Thinking Machines' Inkling 2 Small on its first day of release

    vLLM provides support for Inkling 2 Small on its first day of release. The model is a multimodal MoE with text and visual inputs, featuring a total of 594B parameters, 17B activation parameters, a maximum context length of 1M tokens, and comes with a built-in DSpark beam decoder.

    Why it matters: The original text provides details of vLLM's Day-0 support for Inkling 2 Small and multiple kernel optimizations, allowing readers to understand the deployment path and throughput performance of the model.

  4. Databricks Blog60

    Databricks introduces Lakehouse//RT, aimed at real-time analysis loads for agents.

    Databricks has released the Lakehouse//RT, designed to directly handle high-concurrency real-time queries brought by AI agents on lakehouses, currently in beta. The official claims it can provide latency below 100 milliseconds under 12,000 QPS, and through four paths—high concurrency, rapid execution, small-step scaling, and a single system—ensures that cost growth is slower than query volume growth.

    Why it matters: The original text provides four cost reduction mechanisms and migration data from three customers, allowing judgment on whether the real-time analytics layer is worth replacing.

  2. AWS Machine Learning Blog60

    AWS open-sources UAEF: cross-framework closed-loop evaluation AI agents

    AWS releases open-source framework UAEF, using adapters to unify the execution traces of LangGraph, LangChain, Strands Agents, Amazon Bedrock AgentCore, and Langfuse into AgentTrace, then scoring with 7 dimensions and 36 built-in metrics.

    Why it matters: The original text provides an adapter and metric design for cross-framework unified evaluation, allowing readers to judge the implementation method for comparing multi-framework agent versions.

  1. Databricks Blog76

    Databricks upgrades Genie One to an enterprise AI collaboration workspace

    Databricks announces Genie One as the unified entry point for enterprise AI collaboration, consolidating search, product generation, and cross-tool operations into one place, and providing enterprise context based on Genie Ontology, governed by Unity Gateway.

    Why it matters: The original text provides specific capabilities of Genie One from Q&A to product generation, cross-tool execution, and governance, allowing for judgment on how enterprise AI workbenches can be implemented.

  2. Databricks Blog66

    Databricks has announced that Genie Ontology is now officially available.

    Databricks announces the official availability of Genie Ontology, where agents continuously learn business context from dashboards, SQL queries, notebooks, and semantic models, and key definitions are managed by humans through Unity Catalog.

    Why it matters: The original text provides pass rates, time consumption, and token comparisons for benchmarks co-built with Turing, allowing judgment on the impact of the enterprise context layer on the accuracy of agents.

  3. Databricks Blog80

    Databricks releases new Genie: an autonomous AI colleague for complex enterprise work

    Databricks released a new version of Genie, positioning it as an autonomous AI colleague that can continuously track progress, follow up on missing inputs, and take action when new information arrives. Users can set guards and approve critical steps. The new version is paired with Genie Ontology, which provides business definitions and organizational knowledge. Genie Search uses a hybrid search combining indexing and MCP, and continues to use Unity Catalog permissions. Unity Gateway manages access, cost, and auditing uniformly.

    Why it matters: The original text outlines the boundary of Genie's ability to shift from an assistant to autonomously performing long-term tasks and its governance methods, which can be used to determine the context and permission controls needed for enterprise agents to go live.

  4. OpenRouter Blog70

    OpenRouter tutorial: How to fix OpenAI and Claude's 429 rate limit error

    OpenRouter published a tutorial explaining how to read the 429 response header and determine the rate limit source based on limit_source, providing three repair methods: retry, model fallback, and vendor failover.

    Why it matters: The author used the same batch of 60 requests to test three 429 handling methods, providing a comparison of time consumption and cost, which can be directly migrated to your own retry logic.

  1. QbitAI72

    Baidu Wenxin has first disclosed the progress of RSI, and ERNIE Evolve has been used in the development of Wenxin 5.5 Flash.

    Baidu Wenxin first disclosed its automatic research system ERNIE Evolve, which can autonomously propose research directions, conduct experiments, and validate results. It has been used for inference optimization in Wenxin 5.5 Flash. In the low-latency scenario optimization for Kunlun Chip P800, ERNIE Evolve took about 168 hours and went through 4 rounds of direction exploration, with the optimal version's generation speed increasing to 623.6% of the baseline. The deterministic reasoning throughput optimization increased the throughput to 133.7% of the baseline in 3 days.

    Why it matters: Baidu has disclosed the architecture and production environment optimization data of the automatic research system ERNIE Evolve, which can observe the actual landing points of RSI in inference optimization.

  2. NVIDIA Newsroom78

    NVIDIA released the GR00T 2 world action model and Isaac Lab 3.0 on CoRL.

    NVIDIA released the open-source world action model GR00T 2 on CoRL, built on NVIDIA Cosmos, trained with 100,000 hours of NVIDIA open-source first-person human data, and can complete 40 out of 50 evaluation tasks without task-specific demonstrations.

    Why it matters: The original text provides the success rate of GR00T 2 on few-shot tasks and the training throughput improvement of Isaac Lab 3.0, which can be used to judge the extent to which simulation training promotes robot deployment.

  3. Google Developers Blog65

    Google details Pathways: a single controller training system for large models.

    Google announces Pathways is now generally available on Google Cloud Platform, which is Google's distributed system used to train its own large models like Gemini.

    Why it matters: Google engineers explain the single controller execution model of Pathways and provide a layered difference with Ray for judging the selection of large-scale training orchestration.

  4. Hacker News · 300+78

    llama-modchip enables the 284B DeepSeek-V4-Flash to run on a 64GB memory without GPU

    llama-modchip releases a set of ggml/llama.cpp core patches and quantization transcoding tools, compressing the 284.33B DeepSeek-V4-Flash to 56.56 GiB (1.71 bpw), which can run on a pure CPU machine with 64 GB memory, with a peak memory of 57.61 GiB under 256K context and no need for swap.

    Why it matters: The project provides a quantization scheme and core patches for running 284B MoE on 64 GB memory, along with measured data for each hardware, which can be used to determine the feasible boundary for pure CPU deployment.

  2. Cursor Changelog60

    Cursor online with real-time voice calls to agents

    Cursor launches Voice Chat, allowing users to have real-time voice calls with agents, dictate modification requests, ask what the agent is doing, and receive progress updates.

    Same story · 2 outlets

    Why it matters: Officially, it explains which platforms the voice call is available on and how to divide tasks with coding agents, allowing readers to judge which collaboration scenarios it suits.