AI News
Signal over noise. Daily.
一線 AI Lab
14 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.
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…
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 your metrics, logs, and traces backends to match your monitoring requirements. 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
Intercept and control agent behavior with hooks
Intercept and customize agent behavior at key execution points with hooks Hooks are callback functions that run your code in response to agent events, like a tool being called, a session starting, or execution stopping. With hooks, you can: * **Block dangerous operations** before they execute, like destructive shell commands or unauthorized file access * **Log and audit** every tool call for compliance, debugging, or analytics * **Transform inputs and outputs** to sanitize data, inject credentials, or redirect file paths * **Require human approval** for sensitive actions like database writes or API calls * **Track session lifecycle** to manage state, clean up resources, or send notifications Something happens during agent execution and the SDK fires an event: a tool is about to be called…
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 enabled by default. When tool search is active, tool definitions are withheld from…
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 |
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
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. 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. Check `deny` rules (from `disallowed_tools` and settings.json). If a deny rule matches, the tool is blocked, even in `bypassPermissions` mode. Bare-name deny rules like `Bash` remove the tool from Claude's context…
AMIE, our research medical AI system, demonstrates real-time clinical video consultation capabilities in a first-of-its-kind study.
Google introduces AMIE for real-time clinical video consultations in simulated settings.
Claude Code on Console to Enterprise migration
Overview This guide is built for teams migrating from Console-based Claude Code access to Claude Enterprise. Note that individual users don’t need to migrate session history for CLI sessions since these are stored locally. You only need to provision Claude Enterprise accounts for each user, and then users should switch their login method from Console to Claude Enterprise. Why migrate to Claude Enterprise Claude Code on the Console API is a fast way to get developers started, but it leaves governance up to each individual machine. Claude Enterprise puts the same Claude Code your developers already use behind the controls that security, IT, and finance teams need to run it at scale. You get centralized identity and access through your existing IdP, server-managed settings that enforce tool,…
Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Research Note: CARE-X is a research model and not a Microsoft product offering or medical device. It has not been cleared or approved by any regulatory authority and is not intended for clinical diagnosis, screening, or patient care. The results described below are retrospective research findings and do not establish the safety, effectiveness, or suitability of CARE-X for any clinical use. References to potential workflows describe areas for future research, not currently available capabilities or recommended uses. At a glance The challenge: Chest X-ray interpretation spans diverse tasks that require both expressive report generation and calibrated diagnostic predictions. CARE-X is a unified chest X-ray VLM for diverse clinical interpretation tasks. It combines generation and structured…
Thinking of ACE? We Can Do It with Fewer Tokens
A Blog post by IBM Research on Hugging Face
Testing ads in ChatGPT
OpenAI begins testing ads in ChatGPT to support free access, with clear labeling, answer independence, strong privacy protections, and user control.
Daybreak models are now available on AWS
OpenAI and AWS are making Daybreak cybersecurity capabilities available through Amazon Bedrock to support enterprise security workflows.
媒體
30 articlesBrad Lightcap, a Top OpenAI Executive, Steps Down
Brad Lightcap, a longtime leader, said he was starting a new venture. His exit from the artificial intelligence company is the latest in a series there.
A.I. Offers Hope for Men With Infertility, Spotting ‘Hidden’ Sperm
New technology may make it easier for men with extremely low sperm counts to have biological children.
Accel closes oversubscribed $550M India fund within weeks, 19 months after its last
The U.S. VC firm still has more than 55% of its previous $650 million India fund available for deployment.
Spotify Will Label A.I. Artists and Avoid Promoting Them
The new label, which will begin to be applied next month, is an effort by the streaming service to be more transparent about A.I.-generated music on its app.
Gemini becomes Google's fastest-growing product ever as it hits 1B users
Google has been all-in with Gemini for the last several years, and despite some animosity online, the bet is paying off. CEO Sundar Pichai announced today that Gemini has reached 1 billion monthly active users (MAUs), an important milestone for any Google product. While 13 other Google products have managed that feat, Gemini has done it faster than any other. Gemini has wormed its way into virtually every Google product and service, powering email organization in Gmail, document summary in Drive, and much more. Gemini is also core to Google's flagship search experience, with AI Mode and AI Overviews becoming increasingly hard to avoid. The 1 billion-user metric has nothing to do with any of that, though. These 1 billion users may also be encountering Gemini in all those places, but that's…
ChatGPT and Gemini both just passed 1 billion users
That’s a lot of people chatting with their AI friends all day. | Image: Google For the 14th time, a Google product has hit 1 billion users. Google CEO Sundar Pichai posted on X that a billion people are using Gemini every month, and that Gemini is Google's fastest-growing product ever. A billion users is a huge milestone, but Google isn't the first AI app to hit it. OpenAI's ChatGPT hit the mark a few weeks ago, though the company buried the announcement that "more than 1 billion people are putting ChatGPT to work" in an otherwise anodyne blog post about how people use AI. External data suggested ChatGPT crossed 1 billion users as early as this June, but OpenAI hadn't announced anything until that post on August 6th. … Read the full story at The Verge.
OpenAI launches ChatGPT desktop app for Linux
OpenAI is finally bringing a dedicated ChatGPT desktop app to Linux operating systems.
Reducing Childhood Vaccinations Is ‘Unconscionable’
“The president’s action will kill children,” a doctor writes. “This is not hyperbole.” Also: President Trump and A.I.; support for global health.
Google’s Gemini app surges to 1 billion users
Google also shared numbers of how people are actually using the chatbot, with 63% of Gemini users talking directly to the assistant using the voice feature. Plus, Gemini now generates more than 150 million images every day, according to Google.
Another OpenAI executive takes off
Brad Lightcap, OpenAI's special projects lead and the company's former COO, announced his departure after an eight-year stint at the AI lab. In an internal memo he later posted to X, Lightcap told colleagues he'd be starting "something new." "Over the last few months, I've been focused on the next horizon and what would stand in the way of mission success," Lightcap wrote. "I believe there are a few important new things the world will need to get right as we enter this next period. I … am excited to help you all advance the mission from a different vantage point." He added that he'd still be around for the next few weeks. Lightcap's role … Read the full story at The Verge.
Brad Lightcap, OpenAI’s longtime COO, is leaving to ‘start something new’
One of OpenAI's longest-serving executives is headed out the door, although the longtime COO told staff that he was "excited to help you all advance the mission from a different vantage point."
General Catalyst leads $1.1B round into 2-month-old River AI
River AI, a startup founded by xAI co-founder Igor Babuschkin, has a fascinating vision for personal agents and secured $1.1 billion out of the gate.
Made by Google 2026: all the Pixel news and announcements
Google is gearing up to reveal a bunch of new Pixel devices on August 12th. A series of leaks leading up to the event suggest that the Pixel 11 lineup will come in an array of colors , with signs pointing to a built-in light coming to Pro models . Teasers from Google also indicate that it will show off a next-gen Pixel Fold alongside a Pixel Watch 5 in four different finishes. There might be a new Pixel Tag tracker as well. Google may take the wraps off the new devices well ahead of its Made by Google livestream. On Google’s website , the countdown for preorders ends on August 12th at 10AM ET — eight hours before its event at 6PM ET. Comedian Trevor Noah will host this year’s show, featuring notable guests like NBA star Stephen Curry, podcaster Alex Cooper, Indian cricketer Shubman Gill,…
An unreleased Anthropic model made progress on one of math’s biggest unsolved problems
For more than 150 years, the Riemann hypothesis has stood as one of the major unsolved problems in mathematics. Anthropic hasn't solved it — but the company's models made more progress than you might expect.
Apple could help you prove your iPhone photos aren’t deepfakes
Apple is seemingly developing an iOS feature that can verify when a photograph was taken using an iPhone camera. 9to5Mac reports that the iOS 27 beta 5 includes code references for an "Apple Reference Image" system that can embed provenance metadata into iPhone photographs at the point of capture - enabling users to prove where the photo originated, and that it isn't AI fakery. Apple Reference Image isn't currently live, but a privacy disclosure in the iOS beta notes that the feature will be off by default. When (or if) it does roll out, 9to5Mac says it can be enabled via Settings > Camera > Reference Image > Reference Mode, and that only p … Read the full story at The Verge.
‘Zoomsday’ hack uncovered using fewer than 20 AI prompts
Zoom has patched a major security vulnerability that could allow an attacker to hijack anyone's device during a meeting. In a blog post on Tuesday , researchers at A Security say they uncovered the flaw using "fewer than 20 prompts on publicly available AI models," as reported earlier by Wired . The exploit involved Zoom's annotation feature , which allows users to draw on their screen while sharing it with other meeting participants. With the exploit, an attacker could join or host a meeting and run malicious code on victims' devices, allowing them to steal data, turn on the camera or microphone, or install malware. The attack required no act … Read the full story at The Verge.
His Start-Up’s Goal: A.I. That Is Trainable and Not Controlled by a Big Company
A co-founder of xAI is going all in on building open-source artificial intelligence so that “anyone can control and shape A.I. for their own needs.”
Why your Amazon order confirmation emails have become so unhelpful
Earlier this summer, Amazon customers began noticing that emails related to their online orders looked sparse: Order confirmation emails didn't name specific items anymore, and instead listed only item categories. "Your Beauty item is confirmed!" an email about my retainer cleaning tablets read. Shoppers have posted other iterations of the redacted emails as well: " Ordered: 1 Hardware item ," " Your Drugstore, Shoes, and other items are here! " and " 1 Nutrition & Wellness, 1 Wireless Accessories ," for example. The emails have clip art-style illustrations of general product categories, and a shopper has to exit their email and go to Amazon to … Read the full story at The Verge.
Spotify says it won’t recommend music from ‘AI Personas’
Spotify will soon label AI artists and remove their music from your recommendations. The change, which will start rolling out in mid-September , means you'll see an "AI Persona" badge on an artist's profile across the app if they do "not represent a real person." The music streaming platform will allow artists to disclose that they're an AI persona starting today, but it won't rely solely on self-identification. Spotify says it will use human review and AI tools to determine whether someone's profile, including their name and image, "appears to represent photorealistic AI-generated identities." If Spotify determines that an artist's identity … Read the full story at The Verge.
Spotify will label ‘AI Persona’ profiles and exclude their music from recommendations
Spotify is introducing “AI Persona” labels for artist profiles that represent AI-generated identities and will exclude their music from editorial, algorithmic, and personalized recommendations by default.
A Zoom Screen-Sharing Bug Let Anyone Take Over Other Devices on a Call
Researchers say it took fewer than 20 prompts for a public AI tool to find a flaw (now fixed) allowing anyone on a Zoom call to hijack another participants’ device.
Claude will apply invisible watermarks to AI text and images
Anthropic has pledged to start marking Claude-generated text and images with machine-readable data, in an effort to comply with European rules for AI transparency. "Generated text will carry embedded watermarks, and generated files will include digitally signed provenance metadata where supported," Anthropic says on a new Claude support page . The changes are invisible to human eyes, but will make it easier for people and online platforms to detect if content was generated by Claude models. These updates are a future commitment rather than something that will go into effect immediately. New AI labeling and transparency obligations under the … Read the full story at The Verge.
Anthropic says it will watermark text generated by its AI models
Anthropic will extend support for watermarking AI generations for older models as well.
The Perils of Wall St.’s Race to Pour Billions More Into A.I.
Investors including BlackRock have committed an eye-popping amount to lend to the artificial intelligence industry. That enthusiasm isn’t shared by everyone.
The AI takeover of mathematics has begun
Mathematician James Maynard has spent a lot of time this past year "soul searching." A professor at the University of Oxford and winner of the prestigious Fields Medal, Maynard told The Verge he's been grappling with the future of his field as the traditionally slow-moving discipline hurries to adapt to AI. Days before we spoke, OpenAI revealed it had produced the solutions to 10 long-standing mathematics problems, some of which had confounded academics for decades. Like generative AI used to produce text and images or propose ideas in science and medicine , the technology learns patterns and connections from the vast amount of material it' … Read the full story at The Verge.
A New Trick Reveals AI Models’ Inner Thoughts
Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates that some Chinese AI may be trained on leading US models.
AI Is Dead. Organoids Are Alive
Mini human brains are being grown in labs all over the world. Soon, they could outthink neural networks.
Using A.I. to Stop the Demolition of an Old Steam Plant
Two Roosevelt Island residents used the technology to help them file a lawsuit against the city. They made sure there were no references to made-up precedents.
The Right Loves the Founding Fathers. They Might Love the A.I. Versions Even More.
Glenn Beck and other pundits are turning figures like George Washington into supposedly infallible podcasters.
AI Is Helping Solve the Intricate Genetic Puzzle of Schizophrenia
Recent findings provide one of the most detailed pictures to date of the genetic architecture of schizophrenia, opening up new avenues for research into the disorder.