全部 AI 动态

推荐理由：来自OpenRouter Announcements的《Server-Side Code Execution Tools for AI Agents, ComparedA server-side code execution tool runs the model's commands in the provider's sandbox during your API request, so you don't provision or secure a container. OpenAI, Anthropic, and Google run code for their own models. Our openrouter:shell tool runs commands for any model on the Responses and Messages APIs, and our openrouter:bash tool does the same on the Messages API. This article compares the four on runtime, isolation, persistence, and cost, shows a complete request against our sandbox with the output it ret

推荐理由：来自Claude Code Releases的《Claude Code Releases v2.1.289：Fixed a deny or ask rule on a nested part of a compound sh...》。重点看文化创意。摘要提到：这条英文动态主要涉及文化创意。原文要点：What's changed Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines Fixed the terminal freezing on short code blocks with many unclosed tags or deeply nested ${ substitutions Fixed Read deny rules not applying to files @-mentioned, changed, or selected in the IDE through a symlink [VSCode] Reverted a 2.1.288 chan...

推荐理由：来自Claude Code Releases的《Claude Code Releases v2.1.288：Added $.ui.selection() for mods: returns the text you last...》。重点看开源生态、产品发布。摘要提到：这条英文动态主要涉及开源生态、产品发布。原文要点：What's changed Added $.ui.selection() for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row Added a built-in gh api to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal Added recovery for a prompt cleared with Ctr...

推荐理由：来自GitHub Changelog的《Copilot code review: API support and new default effort level》。重点看开源生态、产品发布。摘要提到：这条英文动态主要涉及开源生态、产品发布。原文要点：You can now request a GitHub Copilot code review through the REST and GraphQL APIs and set the review effort level for each request. Balanced is also now the default… The post Copilot code review: API support and new default effort level appeared first on The GitHub Blog .

推荐理由：来自GitHub Changelog的《Selected models in GitHub Copilot deprecated》。重点看智能体工作流、模型能力与工程、开源生态。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、开源生态。原文要点：As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model… The post Selected models in GitHub Copilot deprecated appeared first on The GitHub Blog .

推荐理由：来自OpenAI News的《A model guide for the GPT-6 family》。重点看智能体工作流、模型能力与工程、文化创意。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、文化创意。原文要点：Learn how startups can choose GPT-6 models, tune reasoning effort, improve prompts and skills, coordinate tools, and prepare workflows for production.

推荐理由：来自GitHub Blog AI的《AI is changing developer work. Here are three skills to strengthen.》。重点看智能体工作流、开源生态。摘要提到：这条英文动态主要涉及智能体工作流、开源生态。原文要点：Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow. The post AI is changing developer work. Here are three skills to strengthen. appeared first on The GitHub Blog .

推荐理由：来自Google AI Blog的《The latest AI news we announced in September 2026》。重点看AI。摘要提到：Here are Google’s latest AI updates from September 2026 这条动态来自 Google AI Blog，可重点关注其对 AI 应用和产业节奏的影响。

推荐理由：来自Cloudflare AI的《Introducing Web Search API via AI Gateway》。重点看模型能力与工程、文化创意、产品发布。摘要提到：这条英文动态主要涉及模型能力与工程、文化创意、产品发布。原文要点：Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI Gateway, REST APIs, or Workers bindings.

推荐理由：来自Apple Machine Learning Research的《Language Discrimination Improves Linguistic Learning in Multilingual Speech Models》。重点看模型能力与工程。摘要提到：这条英文动态主要涉及模型能力与工程。原文要点：Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic m...

推荐理由：来自OpenRouter Announcements的《LangChain vs CrewAI: Orchestration Compared to OpenRouter-Native RoutingMulti-model orchestration is three layers. Workflow orchestration is planning, state, memory, and delegation, and LangGraph and CrewAI are built for it. Model routing is choosing a model per call and falling back when it fails, and provider routing is choosing which provider serves that model. OpenRouter does the second two. This article separates the layers, shows the same two-step pipeline in direct OpenRouter calls and in LangChain, and describes when to add a framework, when to use our Agent

推荐理由：来自OpenRouter Announcements的《Model Routing for Support Bots: Cheap-First FAQ Handling》。重点看模型能力与工程、文化创意。摘要提到：这条英文动态主要涉及模型能力与工程、文化创意。原文要点：How to

推荐理由：来自Apple Machine Learning Research的《Limits of Confidence in Diffusion》。重点看模型能力与工程。摘要提到：这条英文动态主要涉及模型能力与工程。原文要点：Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the trainin...

推荐理由：来自OpenRouter Announcements的《Agent Frameworks Compared: Tool-Calling Schema HandlingOpenAI, Anthropic, and Google each use a different request and response shape for the same tool. Agent frameworks handle that difference in different places. Some translate one definition into each provider's format, some are native to a single provider, and some hand the question to a connector underneath. This article compares six frameworks on schema definition, translation, and MCP support, then shows how OpenRouter normalizes tool calling at the API layer so a model swap is a change to one string.October 2,

推荐理由：来自OpenAI News的《Chatham scales its capital markets expertise with OpenAI》。重点看智能体工作流、产品发布。摘要提到：这条英文动态主要涉及智能体工作流、产品发布。原文要点：Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.

推荐理由：来自OpenRouter Announcements的《Model Router Benchmarks》。重点看模型能力与工程、评测与基准。摘要提到：这条英文动态主要涉及模型能力与工程、评测与基准。原文要点：Compare model routers like Auto Router, Jev Router, Pareto, Fugu, and Switchyard across six benchmarks. The Router Index weighs quality, speed, and cost on one 0 to 10 scale.

推荐理由：来自GitHub Changelog的《GitHub Copilot can now interact with desktop apps with computer use》。重点看开源生态。摘要提到：这条英文动态主要涉及开源生态。原文要点：Computer use is now available in public preview in GitHub Copilot CLI and the GitHub Copilot app on macOS and Windows. Copilot can interact with desktop applications on your behalf… The post GitHub Copilot can now interact with desktop apps with computer use appeared first on The GitHub Blog .

推荐理由：来自GitHub Changelog的《GitHub Actions: macOS 14 runner image retirement》。重点看开源生态。摘要提到：这条英文动态主要涉及开源生态。原文要点：The macOS 14 runner image will be retired on November 2, 2026. To raise awareness of the upcoming removal, jobs using macOS 14 will temporarily fail during the following scheduled… The post GitHub Actions: macOS 14 runner image retirement appeared first on The GitHub Blog .

推荐理由：它和智能体工作流、开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：来自Claude Code Releases的《Claude Code Releases v2.1.287：Added Claude Mods: plugins may now modify deeper behavior ...》。重点看智能体工作流、文化创意。摘要提到：这条英文动态主要涉及智能体工作流、文化创意。原文要点：What's changed Added Claude Mods: plugins may now modify deeper behavior Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with /plugin enable cc-plugin-you-should-know@builtin (for first-party sessions with telemetry on) Added an n: filter to the agents view that matches session names and tasks; a filter now sho...

推荐理由：它和智能体工作流、文化创意、开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：它和开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：它和智能体工作流、开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：来自OpenAI News的《How Albertsons Companies is reimagining retail from the inside out》。重点看产品发布。摘要提到：这条英文动态主要涉及产品发布。原文要点：Albertsons Cos. is using ChatGPT Enterprise and the OpenAI API to help teams work faster and make grocery shopping easier for millions of customers.

推荐理由：来自Cloudflare AI的《Introducing Clef: our open-source decision models, and new RL fine-tuning platform》。重点看智能体工作流、模型能力与工程、产品发布。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、产品发布。原文要点：We are introducing Clef and Clef-flash, open-source decision models hosted on Workers AI for high-speed classification and agentic workflows. Also launching: a new reinforcement learning platform that allows developers to fine-tune decision models using their own data.

推荐理由：来自Cloudflare AI的《One year later: Sovereign AI and the fight for choice》。重点看模型能力与工程。摘要提到：这条英文动态主要涉及模型能力与工程。原文要点：AI sovereignty is not a zero-sum game, but many governments now believe it is. Cloudflare's answer: more local open-source models, model-agnostic security tools, and a commitment to giving nations genuine choice.

推荐理由：它和开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：来自Cloudflare AI的《Cloudflare OS: your company’s agent workspace, managed for you》。重点看智能体工作流、产品发布。摘要提到：这条英文动态主要涉及智能体工作流、产品发布。原文要点：Cloudflare OS gives everyone in your organization an agent workspace that knows how your company works and connects to its data and systems. We’re opening the waitlist for fully managed deployments that you’ll be able to launch in a few clicks.

推荐理由：来自Cloudflare AI的《AI Search is now generally available》。重点看模型能力与工程。摘要提到：这条英文动态主要涉及模型能力与工程。原文要点：AI Search is now generally available. It embeds image pixels directly for visual search, runs optical character recognition on scanned PDFs, accepts files up to 10 MiB, and works with any chat model. Here's what's new and how pricing works.

推荐理由：来自Apple Machine Learning Research的《RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback》。重点看智能体工作流、模型能力与工程、教育应用。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、教育应用。原文要点：The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones. This becomes problematic in the realms of self-improvement, where tasks are so difficult that the agent has a low or even no chance of success, and where there are no teacher models or example solutions to distill f...

推荐理由：来自OpenAI News的《The Den frees up 10-15 hours a week to grow with ChatGPT Work》。重点看AI。摘要提到：这条英文动态讨论了 AI 领域的新进展。原文要点：As it opens a new location, the social club prepares grant applications in 2 hours instead of 3 days and liquor-license materials in 3 hours instead of 4 days.

推荐理由：来自OpenRouter Announcements的《Cost vs. Quality Tradeoff Framework for Agent Models》。重点看智能体工作流、模型能力与工程、开源生态。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、开源生态。原文要点：A three-step framework for choosing a model for an AI agent

推荐理由：来自Apple Machine Learning Research的《How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?》。重点看智能体工作流、模型能力与工程、评测与基准。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、评测与基准。原文要点：Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern MLE agents are deployed on top of increasingly elaborate machinery: multi-agent orchestrators, dedicated retrieval subagents, and more. While such ...

推荐理由：来自OpenRouter Announcements的《How to Gate Pull Requests on LLM Evals in CI》。重点看智能体工作流、模型能力与工程、评测与基准。摘要提到：这条英文动态主要涉及智能体工作流、模型能力与工程、评测与基准。原文要点：Keep a fixed eval set in your repository, score it with a script that calls OpenRouter, measure your noise f

推荐理由：它和开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：来自Google DeepMind的《Gemini 4 Argon: our next era of frontier intelligence》。重点看AI。摘要提到：这条英文动态讨论了 AI 领域的新进展。原文要点：Gemini 4 Argon: our next era of frontier intelligence

推荐理由：来自Claude Code Releases的《Claude Code Releases v2.1.286：Added a count such as "2 of 5" to the permission prompt wh...》。重点看模型发布、编码。摘要提到：这条英文动态讨论了 AI 领域的新进展。原文要点：What's changed Added a count such as "2 of 5" to the permission prompt when several permission requests stack up Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expi...

推荐理由：来自Google DeepMind的《Introducing SynthID Bio》。重点看部署/工程。摘要提到：这条英文动态讨论了 AI 领域的新进展。原文要点：Proof of concept for watermarking AI-generated proteins while preserving biological function.

推荐理由：它和模型能力与工程、开源生态直接相关，可能影响产品设计、研究判断、教育/文化场景落地或开发实践。

推荐理由：来自Cloudflare AI的《Simplifying domains for people and agents》。重点看智能体工作流、产品发布。摘要提到：这条英文动态主要涉及智能体工作流、产品发布。原文要点：Cloudflare Registrar’s new search delivers fast, transparent results across 420+ extensions using Workers, Durable Objects, and WebSockets. Its expanded API and cf CLI also let agents search, register, and transfer domains.