GitHub 发布 AI 代码评审开放基准 ReviewBench
GitHub 发布代码评审离线基准 ReviewBench，基于 1.039 亿个 GitHub PR 的分布特征，构建了覆盖 19 种语言、219 个公开 PR 的评测集，并公开数据集、评分规则与 LLM 评审模型配置。
Awaiting translation
Why it matters: GitHub 公开了 AI 代码评审基准的数据集、评分规则与评测入口，读者可据此对比不同评审智能体。
10/6 · Tue
Selected
Latest curated items
GitHub Blog · CopilotSelectedAI score6666
TonyBaiSelectedAI score8080 Pi 1.0 is out: the Agent engine behind OpenClaw now takes in MCP and ships Pi Durable with crash recovery
On October 1, the Earendil team released the Agent Harness Pi 1.0, with roughly 11.1 stars and 1.4 forks on GitHub, plus an experimental new package called Pi Durable.
Why it matters: Pi 1.0 and Pi Durable bring distributed concepts like checkpoints, idempotent commits, and ownership trees into the Agent runtime, which you can use to weigh the engineering trade-offs of long-running Agents.
cxuanAISelectedAI score8585 Google DeepMind 发布 Gemini 4 Argon，输出上限提至 1M tokens
Google DeepMind 发布 Gemini 4 Argon，单次输出上限从 64K 提升到 1M tokens，主打长任务与多步骤推理。
Awaiting translation
Why it matters: 汇总了 Gemini 4 Argon 的官方评测数据与 Google 内部落地案例，可对照各家旗舰模型的能力差异。
Habr · CodexSelectedAI score7676 OpenAI releases GPT-6.1 Sol, with API pricing at roughly one-fifth of Astra's
OpenAI has released GPT-6.1 Sol for coding, document processing, and task automation. The company says it comes close to GPT-6 Astra on some tests. On DeepSWE 1.1, a benchmark of real-world codebase tasks, the model matches Astra while costing about one-fifth as much to run. On OSWorld 2.0, which tests app control, it beats GPT-6 Sol by 7 percentage points at the highest reasoning tier.
Why it matters: GPT-6.1 Sol matches Astra on DeepSWE 1.1 at roughly one-fifth the cost, which gives you a sense of how the price-performance tradeoff for coding tasks has shifted.
Simon Willison · Coding AgentsSelectedAI score7878 Live from OpenAI DevDay 2026: Dots personal agent, GPT-6.1 Sol, and Ultrafast announced
Simon Willison live-blogged the OpenAI DevDay 2026 keynote from Fort Mason in San Francisco, where OpenAI announced the personal agent Dots, ChatGPT Space, GPT-6.1 Sol, Ultrafast, and more.
Why it matters: A running, item-by-item record of what OpenAI announced at DevDay, for a quick look at what Dots, GPT-6.1 Sol, Ultrafast, and Codex Security actually look like.
Tproger · ПрограммированиеSelectedAI score8888 OpenAI 在 DevDay 发布 GPT-6.1 Sol，价格仅为 Astra 的五分之一
OpenAI 在 9 月 29 日旧金山 DevDay 上发布 GPT-6.1 Sol，API 名为 gpt-6.1-sol，定价为每百万输入 token 2 美元、输出 10 美元，缓存输入 0.10 美元，标准价格是 GPT-6 Astra 的五分之一。
Awaiting translation
Why it matters: OpenAI DevDay 发布 GPT-6.1 Sol，价格降至 Astra 的五分之一，并同步更新 Codex、Agents API 与插件体系，可据此判断成本与工具链变化。
Tproger · ПрограммированиеSelectedAI score8080 Anthropic Releases Flagship Model Claude Opus 5.5
On September 22, Anthropic released its flagship model Claude Opus 5.5, aimed at developers and teams who want agents to handle multi-step tasks like coding and data analysis. The company says it delivers better performance and lower cost than Opus 5.
Why it matters: Anthropic's published pricing and the default workload cost reduction help developers estimate the migration cost for long-running agent tasks.
Cursor · ChangelogSelectedAI score6262 Cursor Launches Two Bots: Rollouts and Security Review
Cursor has released two bots, Rollouts and Security Review, both available on Team and Enterprise plans.
Why it matters: The official docs cover the monitoring and security review workflows for both bots, so readers can judge whether they fit into their existing delivery pipeline.
Lovable · BlogSelectedAI score6060 Lovable Ships Opus 5.5: Faster Builds, Quality on Par with Opus 5
Lovable has shipped Opus 5.5, which the company says matches Opus 5 in results while cutting the number of steps by one-third to one-half. On Lovable's internal benchmarks, Opus 5.5 ties Opus 5 on 0-to-1 builds and iterative code changes, and comes out 4% to 6% ahead on validation discipline; across all reasoning effort levels, steps per task drop by 26% to 57% and input tokens fall by 21% to 59%, with the differences significant at the 95% confidence level.
Why it matters: Lovable shares official comparison data between Opus 5.5 and Opus 5 on step counts and tokens, so readers can judge the real change in build efficiency.
Lovable · BlogSelectedAI score6464 Lovable open-sources OJ, a Rust preview engine that beats Vite on cold start and memory
Lovable has released OJ, a preview engine written from scratch in Rust. It reads your existing vite.config.ts and runs real Vite plugins through a compatibility layer, all in a single binary, with no toolchain installed into the project.
Why it matters: Lovable rewrote its preview engine OJ in Rust, sharing cold start and memory comparisons against Vite, plus canary data from production.
Cline · BlogSelectedAI score6262 Cline releases the open-source desktop app Cline Desktop, aimed at open-weight models.
Cline has released an early version of its open-source desktop app, Cline Desktop, moving the agent runtime that previously lived in the VS Code extension and CLI into a standalone workspace. It supports parallel sessions, scheduled tasks, and a Marketplace for extending tools and integrations.
Why it matters: The official release lays out the desktop app's capabilities and open entry points, so readers can judge whether it fits their multi-agent parallel workloads.
Cursor · ChangelogSelectedAI score7676 Cursor launches “Projects,” a feature that uses a coordinating agent to take on long-running development work
Cursor introduces “Projects,” a feature built for long-running work like a single feature, a migration, or an entire application. It keeps context over months and delegates tasks to thousands of sub-agents. Projects are powered by cloud agents: the coordinating agent doesn’t write code, it only plans, assigns work, and hands back results, spinning up local agents when on-device testing is needed. Each project keeps a set of files synced between the cloud and local machines, steadily accumulating research findings, artifacts, and knowledge of the codebase.
Why it matters: The official docs lay out the context-sharing and auto-triggering mechanisms for project-based multi-agent collaboration, which you can use to judge how long-running tasks get taken over.
GitHub Blog · CopilotSelectedAI score7171 GitHub Copilot launches Project HydraFusion, using multi-model runtime orchestration to improve coding quality
GitHub has launched Project HydraFusion as a research preview in the Copilot CLI. It uses runtime orchestration to pick an execution plan across models from multiple providers. Users select it just like any other model, and billing follows each model's standard rates.
Why it matters: GitHub lays out three orchestration modes for HydraFusion and compares cost versus quality across three benchmarks, so you can judge the trade-offs of multi-model orchestration on real coding tasks.
DevAgentStack · Field NotesSelectedAI score8282 GPT-6 Astra vs. Fable 5.1 benchmarks: which scores are comparable and which aren't
On September 3, 2026, OpenAI released GPT-6 Astra and Astra Pro, initially limited to enterprises in the Daybreak cybersecurity program, with paid ChatGPT, the API, and AWS opening up over the following days.
Why it matters: We break down the benchmark comparison between GPT-6 Astra and Fable 5.1, pointing out that the tested versions and harnesses differ across teams, so readers can judge which scores are actually comparable.
Cursor · ChangelogSelectedAI score6666 Cursor launches self-hosted machines, keeping tool execution within your own network
Cursor supports self-hosted machines: code repositories, build artifacts, and secrets all stay on internal machines within your own infrastructure, and the agent handles tool calls locally. My Machines connects a single laptop or VM to a personal workflow, while Team Pools are named worker queues for teams or enterprises—scaling capacity up with requests and down when workers disconnect. Pools aren't tied to code repositories, and idle machines can sleep and then resume within a reconnection window.
Why it matters: The official docs lay out pooled scheduling and sandbox integration for self-hosted machines, so readers can judge whether tool execution can stay within their own network.
Cline · BlogSelectedAI score7171 Cline 实测八个模型做 IMO 2026：DeepSeek V4 Flash 以 0.12 美元拿到金牌线
Cline 让八个模型在自家 harness 里做 IMO 2026 六道题，证明由 GPT-5.5 和 Claude Opus 5 双盲按 0–7 分制评分、Gemini 3.1 Pro 仲裁，金牌线为 29 分。
Awaiting translation
Why it matters: Cline 用同一套 harness 盲评八个模型做 IMO 2026，给出分数与单次成本对照，可看开源权重模型的实际性价比。
OpenAI Developer Blog · CodexSelectedAI score6565 OpenAI Releases Daybreak and Codex Security, a Security Workflow
OpenAI has launched Daybreak, combining ChatGPT, Codex Security, and the open-source Codex Security CLI into a security defense workflow that covers pre-merge PR reviews, repository and vulnerability backlog scans, and regular CI checks.
Why it matters: The official documentation walks through the full Codex Security workflow—from PR reviews and repository scans to CLI-based batch scanning—so you can decide how to plug it into your existing security processes.
Cursor · ChangelogSelectedAI score6666 Cursor Updates Cloud Agents and Harness: Event Subscriptions, Independent Sub-Agent Runs, and /goal
Cursor has updated its cloud agents and Cursor harness so cloud agents can subscribe to event sources, resume when there's new activity in a PR, Slack thread, or scheduled task, and keep going until the work is done—fixing CI failures and handling bot comments.
Why it matters: Cloud agents are moving from one-shot runs to subscribing to events and following up continuously on PRs and Slack threads, which gives readers a way to judge how the boundaries of automation are shifting.
OpenAI Developer Blog · CodexSelectedAI score7171 OpenAI open-sources the Codex harness and the app-server client protocol
OpenAI has open-sourced the harness that drives the Codex app, CLI, and IDE extensions, and through the Codex app-server client protocol it exposes capabilities like creating threads, starting turns, receiving events, and handling approval requests.
Why it matters: With the Codex harness and app-server protocol now public, developers can see how to embed the agent in their own products and where the boundaries are.
Cline · BlogSelectedAI score6060 NVIDIA Nemotron 3.5 Lightning Is Now on Cline, Free to Use
NVIDIA has released Nemotron 3.5 Lightning, a customizable open-source model built for persistent agents, and it's now available for free in Cline.
Why it matters: NVIDIA's new open-source model is free to use on Cline, so you can decide whether it's worth switching for high-frequency agent workloads.