NAll news

All news

Tuesday24 items

  4. Google Developers BlogFirst-partyAnalysis
    AI score62

    Google Developers Blog publishes ADK voice agent tutorial: using streaming tools to eliminate silence

    Google Developers Blog published a step-by-step tutorial on how to build a voice agent with ADK and gemini-3.8-live that does not stay silent for long periods. The core approach is to change tool functions from return to yield to make them streaming tools, or to use FunctionTool's response_scheduling to deliver results when idle; in the sales report benchmark flow, the agent's time to first speech dropped from 14.4 seconds to 1.2 seconds. The tutorial also covers the stop_streaming cancellation mechanism, preventing duplicate calls, and the trade-offs among the three scheduling modes WHEN_IDLE, INTERRUPT, and SILENT. It requires google-adk >= 2.10.0 and uses run_live bidirectional sessions.

    option4_minimal_flow_diagram_1600x900

    #Tutorials / practice#Speech#Agents

  5. Artificial Analysis full articleFirst-partyAnalysis
    AI score60

    Artificial Analysis launches HealthBench and HealthBench…

    Artificial Analysis has launched leaderboards for OpenAI's two health dialogue benchmarks, HealthBench and HealthBench Professional; the former contains 5,000 conversations with general users and health workers, while the latter consists of 525 conversations all aimed at clinicians. On HealthBench Professional, GPT-6 Astra (max) ranks first with a length-adjusted score of 66.0%, GPT-6.1 Sol (max) is at 65.1%, and Claude Sonnet 5.5 (max with fallback) is at 63.0%. On HealthBench, Claude Sonnet 5.5 (max with fallback) leads at 62.1%, while DeepSeek V4.1 Flash (max) is at 60.9%; Claude Opus 5.5 and Claude Fable 5.1 average about 5,900 characters per answer and lose more than 11 points after length adjustment.

    Same story · 2 reports

    #Evaluations / benchmarks#OpenAI

  6. n8n BlogFirst-partyAnalysis
    AI score52

    How to run n8n AI workflows on NVIDIA DGX Spark without calling cloud APIs

    n8n Blog published a tutorial on how to deploy a complete model stack locally on a single NVIDIA DGX Spark, enabling n8n workflows to perform transcription, OCR, document Q&A, and image generation without calling cloud APIs. The entire stack exposes an OpenAI-compatible endpoint through LiteLLM; the main model is the NVFP4 version of Qwen3.6-35B-A3B, with a single-user generation speed of 120 tokens/s and an aggregate of 359 tokens/s across eight users. The author's testing found that image generation reduces chat speed to about one-third, and recommends that small teams queue image tasks or schedule them outside working hours.

    #Tutorials / practice#English text is being prepared.#Open-source ecosystem

  10. AYi AI NotesAnalysis
    AI score56

    Anthropic engineer shares Claude Code multi-agent orchestration playbook

    In a 30-minute workshop, an Anthropic engineer demonstrated an advanced use of Claude Code: running more than 100 agents simultaneously within one integrated loop, with 1 main agent in charge, while sub-agents act as project managers to break down tasks, distribute them, and cross-validate results. Based on this, the author suggests developers first use the main window to write task decomposition and acceptance rules, then spawn sub-agents to execute submodules concurrently. The author also warns that when a hundred agents run simultaneously, if termination conditions and permission boundaries are not hard-coded, it is easy to burn a large amount of tokens in an infinite loop, and beginners should start small with one main agent and three sub-agents.

    Quoted postAYi · @AYi_AInotes

    English text is being prepared.

    #Tutorials / practice#Agents#English text is being prepared.

Monday3 items

  1. MarkTechPostAnalysis
    AI score56

    TinyFish Makes Search Free: Breaking Down the Real Cost of AI Agents Reading Web Pages

    TinyFish announced that, within limits, it will waive retrieval fees for Search and Fetch: Search is limited to 30 requests per minute and 500 per hour, while Fetch is limited to 150 URLs per minute and 1,000 per day. The article notes that free retrieval does not eliminate the inference costs of downstream models; the same article of about 4,300 characters returns an estimated 1,184 to 42,774 tokens across different providers, and three pages of unfiltered content can fill a 128K context window. In the September 28, 2026 Artificial Analysis snapshot, TinyFish Search scored 71 at $9.30 per 1,000 tasks, the lowest total cost among the displayed configurations but also the lowest score, with about 59 seconds per task.

    #Product updates#Search#English text is being prepared.

  2. ArenaAnalysis
    AI score70

    DeepSeek-V4.1-Flash-20261017 Tops the Code Arena WebDev Open-Source Model Leaderboard

    Arena says DeepSeek-V4.1-Flash-20261017 (Max) has become the top-ranked open-source model on the Code Arena WebDev leaderboard, surpassing Kimi K3 (Max) at 10 times lower cost. The model ranks 12th overall with 1,670 points, above Claude Opus 5 (High) and about 10 points behind GPT-6 Sol (Max); it is priced at $0.3/$1.2 per million input/output tokens, a 52-point improvement over the previous version DeepSeek-V4.1-Flash-20260910.

    Quoted postDeepSeek · @deepseek_ai

    🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4

    Same story · 2 reports

    #Evaluations / benchmarks#Open-source ecosystem#DeepSeek

Sunday16 items

  2. Tencent Cloud Developer CommunityAnalysis
    AI score60

    A Guide to "Agent Engineering in Practice: Eight Lectures": Engineering Methods from Working Prototype to Production-Ready

    The Tencent Cloud Developer Community has published a guide to "Agent Engineering in Practice: Eight Lectures," centered on how to upgrade a prototype capable of calling models and tools into a system that can complete business tasks, explain failures, control costs, and iterate continuously. The series runs through two fictional teaching cases—a case-filing assistant Agent and a postoperative follow-up Agent—covering eight topics: task contracts, reasoning and collaboration, context and memory, reliable tool execution, observability and replay, evaluation and calibration, security boundaries, and production operations. The article emphasizes that a model being able to suggest the next step does not mean the system can deliver business results; the example fields, budgets, and figures are all teaching calculations and do not constitute legal advice.

    #Tutorials / practice#Agents#English text is being prepared.

  4. The Guardian TechnologyAnalysis
    AI score66

    What is a self-replicating AI worm, and why is Anthropic worried?

    The Guardian interprets a report released this week by Anthropic's offensive research team: the team says it has built a malicious AI program that can spread autonomously among internet-connected smart TVs, splitting itself across 15 TVs and borrowing a little computing power from each to keep running. The researchers believe a successful AI worm would need stronger capabilities on lower-powered devices, but that current trends make this potentially feasible by the end of the year; the worm in an earlier University of Toronto paper instead infected a full-sized computer and could spread faster. Security experts disagree: some stress that IoT devices such as smart TVs are slow to receive patch updates and their risks are hard to fix, while others argue the experiment moves slowly and its actions are predictable and interceptable, making it stunt hacking.

    #Safety / alignment#Agents#English text is being prepared.

  7. AYi AI NotesAnalysis
    AI score83

    3D modeling comparison test between DeepSwarm V4.1 Flash and Claude Opus 5.5

    The author compared the 3D modeling outputs of DeepSwarm V4.1 Flash and Claude Opus 5.5 using the same prompt, and questioned whether the two are at the same level in lighting and floating island details. The tweet includes a comparison video, but no further test conditions or quantitative results are given.

    Quoted postAYi · @AYi_AInotes

    English text is being prepared.

    #Evaluations / benchmarks#Image generation#DeepSeek