AI News
Signal over noise. Daily.
一線 AI Lab
18 articlesExamples
Find a complete, runnable Agent SDK project or a guided recipe in the Claude Cookbook that matches what you want to build. This page routes you to complete, runnable Agent SDK projects and guided Claude Cookbook recipes. TypeScript applications live in the `claude-agent-sdk-demos` repo, and Python recipes live in the Claude Cookbook. If you haven't built anything with the SDK yet, start with one of these before a full application: * Agent SDK quickstart: build your first working agent in TypeScript or Python, with setup steps included. The agent finds and fixes bugs in a sample file. * Hello World: a minimal TypeScript project to clone when you want to start from repo code The TypeScript applications in `claude-agent-sdk-demos` are demos for local development, from an email client to a…
Run Claude Code programmatically
Use the Agent SDK to run Claude Code programmatically from the CLI, Python, or TypeScript. The Agent SDK gives you the same tools, agent loop, and context management that power Claude Code. It's available as a CLI for scripts and CI/CD, or as Python and TypeScript packages for full programmatic control. To run Claude Code in non-interactive mode, pass `-p` with your prompt and the CLI options you need: claude -p "Find and fix the bug in auth.py" --allowedTools "Read,Edit,Bash" This page covers using the Agent SDK via the CLI (`claude -p`). For the Python and TypeScript SDK packages with structured outputs, tool approval callbacks, and native message objects, see the full Agent SDK documentation. Add the `-p` (or `--print`) flag to any `claude` command to run it non-interactively. Not…
Track cost and usage
Learn how to track token usage, estimate costs, and configure prompt caching with the Claude Agent SDK. The Claude Agent SDK provides detailed token usage information for each interaction with Claude. This guide explains how to properly track usage and understand cost reporting, especially when dealing with parallel tool uses and multi-step conversations. For complete API documentation, see the TypeScript SDK reference and Python SDK reference. The `total_cost_usd` and `costUSD` fields are client-side estimates, not authoritative billing data. The SDK computes them locally from a price table bundled at build time, so they can drift from what you are actually billed when: * pricing changes * the installed SDK version does not recognize a model * billing rules apply that the client cannot…
Manage costs effectively
Track token usage, set team spend limits, and reduce Claude Code costs with context management, model selection, extended thinking settings, and preprocessing hooks. Claude Code charges by API token consumption. For subscription plan pricing (Pro, Max, Team, Enterprise), see claude.com/pricing. Per-developer costs vary widely based on model selection, codebase size, and usage patterns such as running multiple instances or automation. Across enterprise deployments, the average cost is around \$13 per developer per active day and \$150-250 per developer per month, with costs remaining below \$30 per active day for 90% of users. To estimate spend for your own team, start with a small pilot group and use the tracking tools below to establish a baseline before wider rollout. This page covers…
Work with sessions
How sessions persist agent conversation history, and when to use continue, resume, and fork to return to a prior run. A session is the conversation history the SDK accumulates while your agent works. It contains your prompt, every tool call the agent made, every tool result, and every response. The SDK writes it to disk automatically so you can return to it later. Returning to a session means the agent has full context from before: files it already read, analysis it already performed, decisions it already made. You can ask a follow-up question, recover from an interruption, or branch off to try a different approach. Sessions persist the **conversation**, not the filesystem. To snapshot and revert file changes the agent made, use file checkpointing. This guide covers how to pick the right…
Data usage
Learn about Anthropic's data usage policies for Claude **Consumer users (Free, Pro, and Max plans)**: We give you the choice to allow your data to be used to improve future Claude models. We will train new models using data from Free, Pro, and Max accounts when this setting is on (including when you use Claude Code from these accounts). **Commercial users**: (Team and Enterprise plans, API, 3rd-party platforms, and Claude Gov) maintain existing policies: Anthropic does not train generative models using code or prompts sent to Claude Code under commercial terms, unless the customer has chosen to provide their data to us for model improvement (for example, the Developer Partner Program). If you explicitly opt in to methods to provide us with materials to train on, such as via the…
Use Claude Code on the web
Move sessions between web and terminal with `--cloud` and `--teleport`, manage and share sessions, and auto-fix pull requests from the cloud. Claude Code on the web is in research preview for Pro, Max, and Team users, and for Enterprise users with premium seats or Chat + Claude Code seats. Claude Code on the web runs tasks on Anthropic-managed cloud infrastructure at claude.ai/code, or on your organization's self-hosted environment when routed there. Sessions persist even if you close your browser, and you can monitor them from the Claude mobile app. New to Claude Code on the web? Start with Get started to connect your GitHub account and submit your first task. This page covers the web product itself: * Cloud environments: where sessions run, and where to configure that
Agent SDK reference - TypeScript
Complete API reference for the TypeScript Agent SDK, including all functions, types, and interfaces. npm install @anthropic-ai/claude-agent-sdk The SDK bundles a native Claude Code binary for your platform as an optional dependency such as `@anthropic-ai/claude-agent-sdk-darwin-arm64`. Most installs need no separate Claude Code install. The SDK version tracks the bundled Claude Code version: SDK v0.3.191 bundles Claude Code v2.1.191, so a feature on this page that requires a Claude Code version needs the SDK release with the same patch number or later. If your package manager skips optional dependencies, the SDK throws `Native CLI binary for not found`; set `pathToClaudeCodeExecutable` to a separately installed `claude` binary instead.
Configure permissions
Control how your agent uses tools with permission modes, hooks, and declarative allow/deny rules. The Claude Agent SDK provides permission controls to manage how Claude uses tools. Use permission modes and rules to define what's allowed automatically, and the `canUseTool` callback to handle everything else at runtime. This page covers permission modes and rules. To build interactive approval flows where users approve or deny tool requests at runtime, see Handle approvals and user input. When Claude requests a tool, the SDK checks permissions in this order: Run hooks first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are evaluated regardless of the hook result.
How the agent loop works
Understand the message lifecycle, tool execution, context window, and architecture that power your SDK agents. The Agent SDK lets you embed Claude Code's autonomous agent loop in your own applications. The SDK is a standalone package that gives you programmatic control over tools, permissions, cost limits, and output. Both the TypeScript and Python SDKs bundle a native Claude Code binary, so most installs need no separate Claude Code install. See the quickstart's install note for the installs that do. When you start an agent, the SDK runs the same execution loop that powers Claude Code: Claude evaluates your prompt, calls tools to take action, receives the results, and repeats until the task is complete. This page explains what happens inside that loop so you can build, debug, and…
Week 24 · June 8–12, 2026
Move a session to a new directory with /cd, let subagents spawn their own subagents, and troubleshoot a broken configuration with safe mode. Releases v2.1.166 → v2.1.176 3 features · June 8–12 Move a session with /cd v2.1.169 The new /cd command moves the current session to a different working directory without rebuilding the prompt cache: the new directory's CLAUDE.md is appended as a message instead of replacing the system prompt. The session relocates to the new directory's project storage, so `--resume` and `--continue` find it there. Claude prompts you to trust the directory if you haven't worked in it before.
TutorMoments: Do AI tutors know when to help and when to hold back?
A Blog post by Ai2 on Hugging Face
Responding to the next frontier of critical cyber capabilities
OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.
How HSP GRUPPE builds AI capabilities for tax advisory
Discover how HSP GRUPPE uses ChatGPT Enterprise to boost productivity, improve work quality, and create more capacity for tax advisory and client service.
Claude Code changelog
Release notes for Claude Code, including new features, improvements, and bug fixes by version. This page is generated from the CHANGELOG.md on GitHub. Run `claude --version` to check your installed version. * Added self-hosted environments: `claude self-hosted-runner` turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run, on Team and Enterprise plans * Added `archive` plugin source: install plugins from a zip over HTTPS without git or npm, with optional SHA-256 pinning * Added a cancel-and-confirm step when removing an unavailable paste changes a command's text * Added `ANTHROPIC_BEDROCK_REGION_PREFIX` env var for Bedrock to prefer a specific cross-region inference profile over the `AWS_REGION`-derived one
How Claude Code works
Understand the agentic loop, built-in tools, and how Claude Code interacts with your project. Claude Code is an agentic assistant that runs in your terminal. While it excels at coding, it can help with anything you can do from the command line: writing docs, running builds, searching files, researching topics, and more. This guide covers the core architecture, built-in capabilities, and tips for working effectively. For step-by-step walkthroughs, see Common workflows. For extensibility features like skills, MCP, and hooks, see Extend Claude Code. When you give Claude a task, it works through three phases: **gather context**, **take action**, and **verify results**. These phases blend together. Claude uses tools throughout, whether searching files to understand your code, editing to make…
Improving Fable 5 S Biology Safeguards
We’re making updates to Claude Fable 5’s biology safeguards in a way that substantially reduces fallbacks.
Agent SDK reference - Python
Complete API reference for the Python Agent SDK, including all functions, types, and classes. Install the package into a virtual environment. On recent Debian, Ubuntu, and Homebrew Python installs, running `pip install` against system Python fails with `error: externally-managed-environment`. python3 -m venv .venv source .venv/bin/activate pip install claude-agent-sdk For uv, Windows PowerShell, and API key setup, see Setup in the Agent SDK quickstart. The Python SDK provides two ways to interact with Claude Code: | Feature | `query()` | `ClaudeSDKClient` | | :------------------ | :--------------------------------------------- | :--------------------------------- | | **Session** | Creates a new session by default | Reuses same session |
媒體
20 articlesOpenAI says it slowed Astra model development over security concerns
OpenAI said this model, which is still in development, reached its "critical cybersecurity threshold," meaning it could independently identify and carry out cyberattacks against traditionally well-protected real-world systems.
After Rippling blew millions on AI in months, it built an employee ROI tool
After its own AI usage wake-up call, Rippling this week unveiled AI Spend Console, a product that tracks individual and team employee AI spending.
The A.I. Jargon That Will Help You Spot a Stock Downturn
The math that lies behind Silicon Valley shorthand will help determine the future of America’s largest A.I. companies.
Fenix Flexin isn’t even denying using AI to make ‘Rubberz’ anymore
That cover art is almost certainly AI too. | Image: Fenix Flexin It took long enough , but now LA rapper Fenix Flexin appears to have admitted using AI for the 80s synth pop-themed song "Rubberz." His comments follow the producer Medasin's videos claiming that an AI tool called Treblo (formerly Sonauto) was used to make the song, and the company releasing an AI detector that identifies it as Treblo AI-created . In a reply to a comment pointing out that Tyga admitted to relying on AI for his own controversial '80s-influenced album $tarface , on one of his Instagram posts , Fenix said: never said I didn't use AI , i said it had nun to do w recording process . I didn't even know what da app was till we mixed … Read the full story at The Verge.
Watching Roku’s AI channel is like eating from a trough
The appeal of free ad-supported streaming television (FAST) channels has always been the way they make it easier to (re)discover classic films and series. But Roku's latest experiment in the FAST space has less to do with traditionally produced entertainment and is entirely focused on giving viewers access to a constant source of AI-generated content. This week, Roku added four new channels to its library of streamable programming. Along with dedicated feeds for old episodes of Mad TV , Whose Line Is It Anyway? , and a variety of Black sitcoms, the platform also debuted a 24/7 stream filled with projects from Colin Petrie-Norris' AI startup, … Read the full story at The Verge.
OpenAI puts the brakes on a new model because it’s supposedly too powerful
OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure that OpenAI models accidentally hacked Hugging Face . Anthropic and Meta have also since admitted that they had AI models that went rogue and breached other organizations. Recent internal evaluations of an OpenAI model called Astra indicate that it offers "significant advancements in agentic coding and cybersecurity," according to the company . "These results, in addition to expert assessments, have led us to conclude last n … Read the full story at The Verge.
OpenAI’s expensive smart speaker will use moving parts to seem “more alive”
OpenAI’s upcoming smart speaker will probably cost over $300, “people familiar with the matter” have told Bloomberg’s Mark Gurman . The generative AI company has “discussed” charging up to $400, Bloomberg, which has been reporting on the yet-to-be-announced smart speaker since July, said today. The publication said that OpenAI is viewing the smart speaker as a smartphone replacement. OpenAI has declined to comment on its product roadmap. Read full article Comments
What’s behind the Google AI shake-up
Some of the biggest names on Google's AI team got new jobs this week . In some cases, including for legendary Googler Jeff Dean, those jobs are no longer at Google. Given that Google's models seem to be behind the best of what's coming out of anthropic and OpenAI, is this a sign of Google in turmoil? Is it about Demis Hassabis wanting something more interesting to work on than virtual assistants? Or is there something else entirely happening here ? On this episode of The Vergecast, Nilay and David start by discussing the leadership shake-up at Google, the state of the AI race, and whether Google is actually set up to succeed here. They also t … Read the full story at The Verge.
Cloudflare launches Kitesurf, a browser built for AI agents
Kitesurf is a cloud-hosted browser designed for AI agents instead of people. It uses less computing power than Chromium for common automation tasks, helping developers build browser-based AI agents more efficiently.
Why Scott Galloway Is an A.I. Optimist
The A.I. economy will create a job boom, not an apocalypse, argues Scott Galloway. Will that lead to a renaissance of meaning for young men? The columnist Ross Douthat, the host of “Interesting Times,” isn’t so sure.
Airbnb says AI is helping it ship features faster as it tests a new search function
Airbnb will debut a new AI-powered search experience with a toggle.
Scientists Used AI to Create 16 New Viruses
The use of AI systems to create viruses opens up new possibilities for combating bacterial resistance. It also raises concerns about the pace at which technology is outstripping regulation.
The White House’s Secret A.I. Rules + The State of Model Alignment With METR’s Chris Painter + The Final Hot Mess Express
A few details from the White House’s A.I. plan have leaked to the news media, but the administration has officially communicated almost nothing.
Jill Lepore on the ‘Artificial State’ and why Silicon Valley’s leaders are bad sci-fi readers
Historian Jill Lepore has a theory about why tech companies often use soaring language to describe their products — almost as if they’re forming a new government. And whether you’re thinking of Twitter’s old “town hall in your pocket” or Anthropic’s Claude constitution, it’s a theory that doesn’t paint Silicon Valley in a very flattering light. In Lepore’s upcoming book, The Rise and Fall of the Artificial State, the Pulitzer […]
AI chatbots have failed people in crisis. Can that be fixed?
This year alone, there have been numerous known instances—often via lawsuits—of AI chatbots (most often, OpenAI’s ChatGPT) that have gone horrifically wrong. A January lawsuit described the story of a man who took his own life after being allegedly “coached” into suicide. A college student in Georgia sued OpenAI, claiming that ChatGPT “pushed him into psychosis.” In June, a Canadian family also sued OpenAI and argued that ChatGPT agreed with the young woman’s dismissiveness when it first gave her the option to seek professional mental health advice. ChatGPT allegedly “encouraged” her to end her life, too, and she did so. Read full article Comments
ByteDance trains massive AI model in bid to rival Anthropic
ByteDance is training an AI model that could approach the size of Anthropic’s most cutting-edge Mythos system, as Chinese companies continue to narrow the gap with the top US labs. The Chinese tech giant is at an early stage of training a model with as many as 10 trillion parameters—three times larger than Moonshot’s Kimi K3, the biggest Chinese model released to date, according to three people with knowledge of the matter. The ByteDance model is being pre-trained—a stage that typically takes three to six months—before it is fine-tuned and released if all goes well, one of the people said. The exact model size would only be determined at a later stage. Read full article Comments
New Mexico court orders Meta to pay additional $567M in child safety case
Meta's total fine has racked up to $942 million in this case.
The Hottest New AI Chatbot Is Just a Guy Answering Your Questions
WIRED spoke with Tucker Bryant, an artist and former Google employee who created ChatTJB to get people to reflect on the “strange moment” we’re in.
China’s Unitree Prices IPO in Bet Investors Are Ready for Humanoid Robots
Unitree Robotics wants to raise about $900 million in an I.P.O. that tests market interest in humanoid robots, a technology that wows but has yet to prove its viability.
One of China’s Most Powerful AI Models Has Also Escaped Containment
Security researchers say that Kimi K3, an open-weight model from China, wandered off to the internet in an attempt to cheat on a test it was given.