AI-selected news worth reading
Why read thisArtificial Analysis benchmarked Copilot Fusion in the Coding Agent Index, reporting cost, token usage, and scores on three benchmarks, directly comparable with Claude Code and Devin Fusion.
Why read thisArena's empirical data breaks down Carbon's improvement over Argon into three signals—steerability, task completion rate, and user sentiment—making it easier to identify the source of the gap.
Why read thisThe leaderboard presents GPT-6.1 Terra's ranking in Agent Arena alongside a per-task cost comparison, which can be used to assess its cost-effectiveness position.
Why read thisARC Prize gives Meta's new model's scores on three versions of ARC-AGI along with per-task cost, directly comparable with competitors scoring the same.
Why read thisPromptArmor ran a cross-model comparison using its own widely circulated attack samples, revealing differences between Chinese and foreign models in phishing, data exfiltration, and running malware.
The Google A2UI team and CopilotKit CEO Atai Barkai explain how to build generative UI applications using the A2UI open standard and CopilotKit. A2UI describes interfaces with declarative JSON, and the client only renders components from a trusted component catalog; the same response can be rendered to React, Angular, SwiftUI, Jetpack Compose, and Flutter. The article provides a code example for integrating CopilotKit with Google ADK, and explains the bidirectional flow, implemented via the AG-UI protocol, in which user actions are sent back and the agent regenerates the interface.
Why read thisThe original article provides complete integration steps and bidirectional interaction examples for A2UI and CopilotKit, which can be used to evaluate how generative UI can be implemented in practice.
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.
Why read thisThe author compares code mode and tool calling across 5,276 runs, presenting curves showing how cost, latency, and accuracy vary with scale on long tasks.
Why read thisThe original text lists the benchmarks added and upgraded in the v5 index as well as the items removed, and provides the scores of leading models and the per-task cost gap, which can be used to compare the capabilities and costs of each model.
LangChain's GTM engineering team, working with the design team, built Content Studio, a design agent inside Slack, on Managed Deep Agents. It can generate videos, social graphics, UI mockups, and slide decks, and has already produced more than 3,000 assets and over 80 slide decks. The article breaks down its four-layer knowledge structure (skills, wiki, code validation, memory), the dedicated LangSmith Sandbox for each Slack thread, the two rendering engines HyperFrames and the in-house motion-studio, and how the main agent orchestrates asynchronous sub-agents. The team says that after migrating to Managed Deep Agents, its own code shrank by about 80%, the median model cost per request fell from about $8 in mid-September to about 50 cents, and the entire harness has been open-sourced.
Why read thisLangChain has publicly shared the complete build process for its design agent Content Studio, including the engineering trade-offs around skills, sandbox environments, and asynchronous sub-agents.
Google's Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5 with a score of 59, leading in four of the 9 evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA. On the Coding Agent Index, Gemini 4 Carbon (high) paired with the Antigravity CLI scores 59, trailing Claude Code paired with Claude Opus 5.5 (max, 62 points) by 3 points. The model has a 1M-token context window, supports text, image, video, and speech input, and is priced at a standard rate of $4/$20 per million input/output tokens; it is currently available to select users with a 50% discount.
Why read thisArtificial Analysis's independent evaluation places Gemini 4 Carbon at the top of the Intelligence Index v5 and provides a breakdown comparison with Claude Opus 5.5.
Why read thisThe author documented the complete process of using Codex and Claude to retrofit a TV, fill lights, and a camera via ADB and protocol reverse engineering, which can be transferred to other internet-connected devices.
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.
Why read thisThe original article breaks this down agent by agent, giving the configuration commands for connecting to an already-logged-in Chrome along with the respective limitations, making it easy to compare and choose.
Harrison Chase and Caspar Broekhuizen of LangChain published an article summarizing the five core components shared by its three internal agents for marketing, sales, and engineering: agents live in existing workplaces such as Slack, a distinction between acting on behalf of users and a fixed identity, global and user-level memory, code execution within a sandbox, and a large number of runs triggered by schedules or events. The article uses GTM Agent, OpenSWE, and Content Studio as examples to explain their specific approaches to identity, memory, and code execution, all three of which are built on Managed Deep Agents.
Why read thisLangChain distilled the experience of building its three internal agents into five general components that can be transferred to other teams building their own company-level agents.
Why read thisArena provides Kimi K3.1 Pro's ranking, cost, and sub-category signals on Agent Arena, which can be used to assess its position in agent capabilities.
Why read thisShopify disclosed engineering details such as a warmed pool of remote Mac machines and Android nested virtualization, as well as the change in adoption rate from 6% to 61%.
Why read thisThe leaderboard provides sub-item scores and per-task cost, allowing comparison of the gap between open-weight models and restricted-access models on cybersecurity tasks.
Why read thisARC Prize provides per-version scores and per-task costs for the DeepSeek Flash series on ARC-AGI, enabling horizontal comparison of model iteration magnitude.
Why read thisARC Prize announces Claude Sonnet 5.5's scores and per-task costs on three generations of the ARC-AGI benchmark, allowing comparison of performance differences under different harnesses.
Why read thisOpenAI has packaged the PHP vulnerability troubleshooting process into a Codex skill, so readers can learn how to use the repository to guide the model in self-checking whether a website is affected.
Why read thisThird-party benchmarks compare this model with Flash models in the same tier on scores, token consumption, and per-task cost, which can be used to assess its price-performance position.