Search “Google”

Gemini 4 Carbon Tops Text Arena, Ranks Second in Agent Arena

Gemini 4 Carbon (High) took first place in Text Arena with 1528 points, surpassing Gemini 4 Argon (High)'s 1520 points. It ranks second in Agent Arena, behind only Claude Opus 5.5, and has entered a new Pareto frontier; in Web Dev Arena it ranks fourth with 1768 points, two points behind third-place Claude Sonnet 5.5. Arena data states its median cost per Agent Arena task is $1.80, 72% lower than top-ranked Claude Opus 5.5 (Max). Its Artificial Analysis V5 score is 59.

Pydantic compares code mode and tool calling across 5,276 runs

Michael Pfaffenberger of Pydantic used 5 small Pydantic AI applications and 8 models to conduct 5,276 scored runs, comparing code mode with direct tool calling. On long tasks, code mode reduced average cost by 58%, latency by 51%, and increased success rate by 16 percentage points; however, for short tasks with 5 items, 3 out of 5 tasks were instead 21% to 38% more expensive. The author argues that models are better at writing loops than at acting as the loop, and the gap widens as tasks get longer.

Perplexity Publishes LLM Gateway Best Practices Guide, Outlining Request Flow and Production Risks

On October 27, 2026, Perplexity published an LLM gateway best practices guide explaining how this middleware layer routes, authenticates, caches, and logs model calls, and distinguishing four categories: API gateways, LLM gateways, MCP gateways, and AI gateways. The guide breaks down the mechanism through a six-step request lifecycle, while warning that the gateway centralizes credentials from various providers, and cites the LiteLLM gateway breach disclosed by Microsoft and two high-severity vulnerabilities, CVE-2026-35029 and CVE-2026-59823, reported by Check Point (already fixed in LiteLLM 1.83.9). The article also lists postmortems of Cloudflare AI Gateway and OpenRouter outages, four deployment paths, and paid plans starting at about $50 per month.

Elorian Releases DecoyCount Benchmark: Frontier Models All Score Below 50% on Visual Counting Accuracy

Elorian and Mercor jointly released the DecoyCount benchmark, which tests whether models truly count objects or rely on visual shortcuts. Frontier models all scored below 50% accuracy, with the highest being GPT-6 Astra at 43.17%. Elorian says its visual reasoning model Glimpse scored 50.48% in a single run on 1,660 questions, making it the only model to exceed 50%, but this result comes from internal testing and did not use an agent or tool framework, whereas the six models in the paper each took the average of three runs. Elorian CEO Andrew Dai said the benchmark examines both vision and reasoning, and can distinguish whether a model failed to see the objects or miscounted them.

How to get coding agents to use your already-logged-in Chrome

Browser Use published a guide introducing several ways to let coding agents work in a real, already-logged-in Chrome, including Claude in Chrome, Playwright MCP extension mode, Chrome DevTools MCP auto-connect mode, the Gemini CLI built-in browser agent, the ChatGPT desktop browser extension, and Browser Harness. The article gives configuration commands and limitations separately for agents such as Claude Code, Codex, Gemini CLI, and Cursor, and explains that starting with Chrome 136, --remote-debugging-port and --remote-debugging-pipe on the default data directory will be ignored, so the old practice of copying cookies to a new browser will fail in scenarios such as device-bound sessions.

DeepSeek V4.1 Flash 1017 Tops the Artificial Analysis Cybersecurity Index Open Model Leaderboard

DeepSeek V4.1 Flash 1017 ranks first among openly available models on the Artificial Analysis Cyber Index with a score of 57%, and second on the overall leaderboard, 12 points behind GPT-6 Sol (69%), which is offered through a trusted access program. The index consists of three benchmarks: CWE-Bench-AA, DeepsecBench-AA, and CyberGym-E2E-AA, and mainly evaluates agentic cybersecurity defense tasks. Compared with the previous generation DeepSeek V4.1 Flash's 41%, the new version improves by 16 points, mainly from CyberGym-E2E-AA rising from 23% to 76%; its cost per task is $0.42, placing it on the capability-cost Pareto frontier.

Kimi K3.1 Pro scores 64% on the Artificial Analysis Cybersecurity Index, ranking first among openly available models

Kimi K3.1 Pro scores 64% on the Artificial Analysis Cyber Index, 7 points higher than the previous leader among openly available models, DeepSeek V4.1 Flash 1017 (57%), and 5 points lower than GPT-6 Sol (Daybreak Blue, max, 69%), which is available only through the OpenAI trusted access program. The index consists of three benchmarks: CWE-Bench-AA, DeepsecBench-AA, and CyberGym-E2E-AA. K3.1 Pro achieves 95% on CyberGym-E2E-AA, higher than GPT-6 Sol (Daybreak Blue)'s 93%. Its per-task cost is $2.81, higher than GPT-6 Sol (Daybreak Blue, max)'s $1.77 and DeepSeek V4.1 Flash 1017's $0.42, because although its per-token price is 33% lower than Kimi K3's, its input token usage is about 2 times as much.

SemiAnalysis benchmarks Trainium3's PyTorch training and Neuron Explorer profiler

The SemiAnalysis engineering team benchmarked the native PyTorch training stack TorchNeuron and TorchTitan on Trainium3, training Qwen3-32B on 16 Trainium2 chips; eager mode reached 11,099 tokens/s and 23.89% MFU, while compiled mode reached 14,156 tokens/s and 30.47% MFU. The author considers the Neuron Explorer profiler superior to Nvidia's and AMD's solutions, but first-time compilation takes too long: the first-step compilation for the gpt-oss training recipe took 27 minutes 17 seconds. FlexAttention tests passed 89 of 96 cases, with all 7 failures due to compilation timeouts rather than numerical errors.

TinyFish Breaks Down Production-Grade Agent Search Architecture and Deep Research Experience

TinyFish released two technical guides: one defines a production-grade agent search architecture, and the other summarizes lessons from building a deep research system. The architecture is built on four web primitives—TinySearch, TinyFetch, TinyBrowser, and TinyAgent—and runs a seven-stage control loop around a foundation model, covering task definition, retrieval planning, tool routing, evidence evaluation, and failure retry. In OpenBenchmarks tests with a fixed gpt-5.6-sol model and 100 tasks, TinyFish search plus fetch achieved a 79.0% completion rate, with a median task cost of $0.050 and a runtime of 24 seconds; under a search-only configuration, the completion rate was 59.3%.

I used Gemini 4 Argon to make 3D-printed armor from a prompt in 18 hours

CNET editor James Bricknell used Gemini 4 Argon to generate, through conversation, a web app that can adjust armor dimensions; after about 10 iterations it reached KeriForge 8.2, then he exported an STL and printed it in TPU 75A. The whole process took about 18 hours, of which printing took 7 hours. The author says Gemini 4 Argon completed complex tasks noticeably faster than his usual Gemini 3.5 Flash-Lite, and that it understood his intent to use the web app offline rather than develop an iPad app. The final print's dimensions matched his forearm and wrist; the surface defects came from the TPU material being too soft and the model being printed too tall, not from the model itself.

9to5Mac reviews the iPhone Duo: the first iPhone in a foldable form factor

9to5Mac editor Chance Miller reviewed Apple's first foldable iPhone Duo after a week of hands-on testing, arguing that this form factor represents the future of the iPhone. When unfolded, the iPhone Duo has a 7.6-inch inner screen; when folded, the outer screen is 5.4 inches. It weighs 254 grams, is 11.3mm thick when folded, is powered by the A20 Pro chip, and costs $1,999. The review notes that it replaces Face ID with Touch ID, lacks a telephoto lens, and that iOS 27 moves navigation controls to the right side and supports Split View on an iPhone for the first time.

MIT Course MAS.S62: Two Lectures on the Evolution of Harnesses and Multi-Agent Systems

Lectures 4-5 of the MIT course MAS.S62 "How to AI an AI" focus on Harness evolution, covering the evolution of harness components, memory, tools, and skills, as well as the evolution of planning, task decomposition, and multi-agent systems. The memory section uses a three-axis taxonomy to connect MemGPT, mem0, MEM1, and Reflexion/ExpeL, and uses CLM to unify context management as file operations; the tools section moves from Toolformer, ToolLLM, and CodeAct to Meta-Harness, which represents the entire harness as a file system and provides about 400 times the amount of feedback information of previous methods. The multi-agent section presents five empirical findings, including that MAS wins 81% on decomposable tasks and loses 70% on tasks with sequential dependencies, and that CORAL achieves new SOTA on 8 tasks, with multi-agent evolution improving over single-agent by 4%-20%.

English translation is being prepared.

English translation is being prepared.

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.