AI News
Signal over noise. Daily.
一線 AI Lab
16 articlesAgent 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.
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…
Claude Code GitHub Actions
Run Claude Code in GitHub Actions workflows to respond to @claude mentions, automate tasks, and turn issues into pull requests Claude Code GitHub Actions is a GitHub Action that runs Claude Code inside your repository's workflows. Mention `@claude` in a pull request or issue comment to have Claude analyze code, implement changes, and push commits. You can also give the Claude Code GitHub Action a prompt to run automatically on any GitHub event. Use it to turn issues into pull requests, fix bugs from a comment, or automate recurring tasks. Several products share the Claude Code name. This page covers the `claude-code-action` workflow integration, which you configure with workflow files in your repository. For the related products, see: * Code Review: automatic review on every pull request,…
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…
Monitoring
Learn how to enable and configure OpenTelemetry for Claude Code. Track Claude Code usage, costs, and tool activity across your organization by exporting telemetry data through OpenTelemetry (OTel). Claude Code exports metrics as time series data via the standard metrics protocol, events via the logs/events protocol, and optionally distributed traces via the traces protocol. Configure OpenTelemetry using environment variables: export CLAUDE_CODE_ENABLE_TELEMETRY=1 export OTEL_METRICS_EXPORTER=otlp # Options: otlp, prometheus, console, none export OTEL_LOGS_EXPORTER=otlp # Options: otlp, console, none export OTEL_EXPORTER_OTLP_PROTOCOL=grpc export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317 export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer your-token" export…
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
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
A Blog post by Amazon on Hugging Face
Introducing Gemini 3.7 Flash
Gemini 3.7 Flash is our most intelligent workhorse model yet for coding and agents.
Bring your spreadsheet data to life with Sheets canvas
Sheets canvas turns data into interactive dashboards, custom study trackers, seating charts, and more, all with a simple prompt.
Scale to many tools with tool search
Scale your agent to thousands of tools by discovering and loading only what's needed, on demand. Tool search enables your agent to work with hundreds or thousands of tools by dynamically discovering and loading them on demand. Instead of loading all tool definitions into the context window upfront, the agent searches your tool catalog and loads only the tools it needs. This approach solves two challenges as tool libraries scale: * **Context efficiency:** Tool definitions can consume large portions of the context window (50 tools can use 10-20K tokens), leaving less room for actual work. * **Tool selection accuracy:** Tool selection accuracy degrades with more than 30-50 tools loaded at once. Tool search is on by default, with the exceptions listed in Configure tool search. When it is…
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 |
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…
The builder’s guide to GPT‑5.6
Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.
OpenAI appoints Dali Rajic as Chief Revenue Officer
OpenAI appoints Dali Rajic as Chief Revenue Officer to lead its global revenue organization and help businesses realize the full value of AI.
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. * Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack * Documented `claude remote-control --continue` for resuming the most recent Remote Control session * Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior * Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams
媒體
35 articlesThe Safety Reckoning Inside OpenAI
OpenAI’s rogue agent hack was a watershed moment for AI safety and cybersecurity. It also sparked internal questions about the culture that led to it.
Microsoft’s Clippy-like Mico character is no longer the face of Copilot
Mico is headed to Learn Live. | Image: Microsoft Microsoft Copilot will no longer show its emotive yellow blob, Mico, when you use the chatbot's voice mode. In a support page , Microsoft says it's going to move Mico to its Learn Live platform, where the avatar will have "more to react to," as reported earlier by GeekWire . Mico launched in Copilot's voice mode last October , with Microsoft AI CEO Mustafa Suleyman pitching the avatar as a way to give the chatbot an "identity." The blob would react to what you say in real-time, complete with facial expressions and animations. Mico joins the long list of virtual helpers that Microsoft has retired over the years, like Clippy, Cortana, and Rover … Read the full story at The Verge.
Only Global Cooperation Can Keep the World Safe From A.I.
A conversation with Robert Wright, the author of “The God Test.”
Another OpenAI Executive, Denise Dresser, Departs the A.I. Start-Up
Denise Dresser, who was previously the C.E.O. of Slack, is the latest in a string of executives to leave the artificial intelligence start-up.
Mark Zuckerberg’s AI Manifesto Is 6,500 Words—and Barely Says Anything
AI is shifting the culture, from tech CEO manifestos to 1 am job interviews. We unpack some of the latest, along with the top findings from Black Hat and Defcon, this week on Uncanny Valley.
Writer introduces new AI model and upgraded harness to contain token costs
Built as a post-training variation on Z.ai's open source model GLM-5.2, Writer says the new system should provide deployment-ready capabilities at a much lower price.
Why A.I.’s Promise Isn’t Resonating
On “The Opinions,” the Yale law professor and economist Natasha Sarin argues that A.I. could transform the U.S. economy for the better. But with the public hearing about layoffs and job losses, she says, it’s no wonder the technology’s economic promise isn’t resonating.
Bryan Johnson’s Blueprint for a 150-Year Life: Is It Worth It?
The tech mogul is trying to design the blueprint for defying death.
Databricks wanted to raise $1B, investors wanted $15B. It settled on $5B at a $190B valuation.
AI is expensive, Ali Ghodsi tells TechCrunch. With so many investors wanting into his latest round, he said yes to more than planned.
OpenAI is losing its second executive this week
Another OpenAI executive is departing. Denise Dresser, who joined OpenAI as its chief revenue officer in December after serving as CEO of Slack, will be leaving in the "coming weeks" to "pursue other opportunities," she said in a team note posted to LinkedIn . Dali Rajic, president and COO of Wiz, will be taking over the CRO role, OpenAI says . Dresser's departure is just the latest in a string of major exits. Earlier this week, special projects lead and former COO Brad Lightcap announced he would be leaving . (Dresser had taken over some of Lightcap's work when he moved to the special projects role.) Former AGI chief Fidji Simo and former CMO … Read the full story at The Verge.
OpenAI introduces ‘Ultrafast,’ a new mode that makes GPT-5.6 Sol work at 14x the speed
OpenAI is launching a preview of a sped up version of its latest, most powerful model, in an effort to court enterprise users.
IBM partners with OpenAI to bolster enterprise AI push
IBM plans to train and certify tens of thousands of consultants on OpenAI's technologies as part of this deal.
Anthropic set AI agents loose on the same task. They started a turf war.
Anthropic researchers found AI agents can clash, collude, and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of multi-agent systems.
The new Instagram logo is the perfect embodiment of AI slop
Today, Instagram unveiled a refresh of its wordmark, accompanied by the usual bland corporate platitudes these kinds of announcements are always packaged with. Head of Instagram Adam Mosseri called it “leaner and more modern, with references to the original and the simplicity and craft that’s always made it Instagram.” Sure, Adam. Simplicity and craft are definitely what everyone thinks of when Instagram comes to mind. Read full article Comments
OpenAI hires new CRO as executive shake-up continues
OpenAI has replaced chief revenue officer Denise Dresser after just nine months on the job, tapping Wiz president and chief operating officer Dali Rajic to take on frontier lab's top sales job.
Google announces Gemini 3.7 Flash just three weeks after previous release
Google is announcing a new Gemini model today, but it's not the long-awaited 3.5 Pro. Gemini 3.7 Flash is now rolling out to replace 3.6 Flash, which itself was released only three weeks ago . This new "workhorse" model is supposedly the product of core optimizations and developer feedback, offering improved coding and agentic performance. And Google is hoping to counter the lower cost of some competing models with a lower "introductory price" for 3.7 Flash. According to Senior Director Tulsee Doshi, Gemini 3.7 Flash is noticeably better at coding than the previous Flash release. She cites a jump in the FrontierCode 1.1 Main test from 34.4 to 43.6 percent and DeepSWE v1.1 going from 49 to 65.3 percent. As for the vibes, Gemini 3.7 Flash's WebDev Arena score has risen to 1,588 from 1,538.…
Suno is trying to look more like a real music production tool
Suno is releasing Studio 2.0 with significant upgrades that push it closer to an actual digital audio workstation (DAW), rather than a bare-bones audio editor with generative AI features. The biggest addition is undoubtedly MIDI support. Suno says that MIDI was its most requested feature, and it's basically a prerequisite for any modern DAW. Unfortunately, Suno Studio doesn't appear to support third-party plugins or VSTs yet, so you're stuck using its proprietary built-in synth. That synth appears to be a basic two-oscillator wavetable plugin with three envelopes and four LFOs. The point is less about using your favorite Arturia vintage syn … Read the full story at The Verge.
A.I. Hype Is Running Into Reality
And what a hedge fund’s $35 billion loss reveals about the state of the industry.
Microsoft kills off unsuccessful AI features while merging its separate Copilot apps
Microsoft is simplifying Copilot by combining its consumer and business apps, and dropping AI-generated podcasts, Group Chats, Deep Research, and its Mico character.
I looked inside an AI generated movie, and the best parts were all human
Imagine a trio of bumbling, English lads who fantasize about becoming megastars while knocking back a few pints in a grimy pub somewhere in London. Picture the guys chortling and trying to one-up each other's idealized visions of the future with a series of increasingly glitzy fantasies in which their fame leads to access to groupies and lavish parties on luxurious boats. Imagine these men are actually characters in a film - one filled with hyperkinetic smash cuts to action sequences in which they're fighting or running from armed goons. This movie might be the sort of feature you'd expect from directors like Edgar Wright or Guy Ritchie. But … Read the full story at The Verge.
Nvidia’s new $500B plan is risky but brilliant, especially for aging GPUs
Nvidia has a plan to make sure its GPUs won't lose value. It wants to convince a new crop of financiers to keep lending for AI buildouts.
Apple in talks to pay publishers to provide Siri with current news: report
The tech giant has considered a nine-figure budget for the payments, according to the WSJ.
If You Weren’t Worried About A.I., You Should Be After the Past Few Weeks
If there was ever a time to consider halting development of A.I., it’s now.
Does Google even want to win at AI?
Today on Decoder , I’m talking with Hayden Field, The Verge ’s senior AI reporter, about a question that’s been rocketing around the tech industry for the past week: Is Google losing the AI race? That’s because last week Google announced a bombshell reorganization of its AI division, Google DeepMind. Jeff Dean, the company’s chief scientist, is leaving to form his own startup and DeepMind cofounder and CEO Demis Hassabis is stepping aside to focus on longer-term research. You can read these moves, and Google’s reaction, in a lot of different ways. So I really wanted to sit down with Hayden to dig into some of the smartest analysis we’ve seen this past week, and what we think is really going on here. Also: At its core, this is an org chart story — and what is Decoder about if not org…
Anthropic could be worth $2 trillion when it goes public
Anthropic investors expect the AI startup to float at a valuation of $2 trillion or more in October, a dizzying figure that would eclipse SpaceX and make the AI lab’s debut the largest-ever initial public offering. Half a dozen of the company’s backers told the FT that Anthropic’s rapidly rising revenue would enable it to more than double its current valuation in a planned autumn float. A listing at that level could unlock billions of dollars in gains for the five-year-old company’s early investors but would also test public markets that are growing more nervous about the AI boom. Read full article Comments
Flock is tightening its rules in response to a growing surveillance backlash
The police-tech giant Flock is announcing today that it will change officers’ access to its nationwide network of license plate readers, in an apparent effort to quell a growing backlash and win back contracts lost amid concerns about mass surveillance and police abuse. Several changes aim directly at a problem that has made recent headlines: officers abusing Flock’s technology to stalk and harass current or former romantic partners. Flock’s 120,000 cameras form a nationwide network that police departments can use, giving officers access to an enormous pool of searchable location data. A recent Washington Post investigation found 46 cases in which officers were accused of using Flock’s cameras for unauthorized purposes like stalking. To combat that, the company will start requiring…
Microsoft is combining its Copilot apps ahead of a ‘super app’
You soon won’t have to look at two Copilot apps in your Windows taskbar. | Image: Microsoft Microsoft is finally beginning to combine its consumer and commercial Copilot AI assistants into a single "super app" interface, starting with the Copilot and Microsoft 365 Copilot apps. Both personal and work accounts will be moved to the new unified app, which recycles the "Microsoft Copilot" name but features an updated app icon. The single app also means there won't be two annoying Copilot icons in the system tray or taskbar anymore. "Starting with a fresh look, the updated app combines the best of Copilot chat and image creation, with the power of Microsoft 365 for your work," Microsoft said in its update announcement . The updates are … Read the full story at The Verge.
We Need Global A.I. Safety Planning
We used to talk about the risks of A.I. a lot more. On a recent episode of “The Opinions,” the Opinion writer David Wallace-Wells speaks with the Yale law professor and economist Natasha Sarin about how A.I. safety could bring China and the U.S. together.
Claude's new Scarlet Letter watermark is invisible—for now
Anthropic has revealed that it will soon watermark content that is processed ( not just generated! ) by any of its models. In a support article , Anthropic explained that it was rolling out machine-readable watermarks to comply with the European Union’s AI Act, which requires all AI system providers to watermark AI-generated or manipulated audio, image, text, and video outputs. The law applies to any AI model released after August 2 and provides a grace period until December 2026 for providers to update previously released models. Anthropic confirmed that moving forward, all new models offered globally—not just in the EU—will mark AI-generated content “from day one.” Text outputs will “carry embedded watermarks,” invisible to the user, and other “generated files will include digitally…
I Tested a Popular A.I. Slop Detector. It Felt Empowering.
Pangram excels at distinguishing chatbot-generated words from human writing. But it’s not reliable for spotting artificial images.
So You Want to Build an A.I. Star?
Designers at a new crop of creative studios create fake personas they hope real people will love. Are they distorting culture or mirroring it?
There’s a Fatty Liver Epidemic. AI Could Help Get Ahead of It
Over a billion people worldwide have livers with excess fat, which can lead to a host of medical problems. Researchers think AI tools can spot the condition—and help stop it—early enough to save lives.
How kids feel about AI, in their own words
When we set out to talk to kids about artificial intelligence, we thought we knew what we’d hear. We expected some to tell us they were using it to cheat a little, the way Millennials and Gen Xers opened up CliffsNotes or programmed formulas into their TI-82s, and others to share inspiring ways they were using it. We were also listening for concerns that were less kid-specific, like deepfakes or job destruction. But what we actually heard when we asked kids aged 10 to 18 about AI had tons of nuance. Many of the same kids who can go on and on about music, rock climbing, or soccer met our questions with words like “bruh” and “meh”—or were so deeply against AI or uninterested in making it part of their lives that they didn’t want to talk about it at all. One teen said his peers use it for…
As Comedians Toy With A.I., Who Will Get the Last Laugh?
Several acts at the Edinburgh Fringe are testing the boundaries of creativity using artificial intelligence.
Thrive Holdings, A.I.-Focused Buyer of Service Firms, Raises $2 Billion
The company, Thrive Holdings, acquires businesses to infuse them with artificial intelligence and drew interest from backers like SoftBank.