AI News & Analysis
Curated takes on AI industry news with perspective
All AI News & Analysis articles
Claude's Memory Now Works Across Chat and Cowork
Claude memory now carries context between Claude chat and Cowork. Anthropic says users can review or remove saved topics, while Team and Enterprise administrators can control the feature for their organizations.
Cursor Cloud Agents Can Now Start Apps From Scratch
Cursor Cloud Agents can now begin a web app without an existing repository. The workflow can create an Origin repository, preview the result, and publish it to Vercel without requiring a local setup first.
ChatGPT Workspaces Can Sync GitHub Plugin Marketplaces Daily
ChatGPT workspace admins and owners can now import plugin marketplaces from public or private GitHub repositories and keep them synchronized automatically. The feature gives teams a central way to distribute Codex and Claude-compatible plugins while keeping installation policies and app permissions under workspace control.
Claude Code Weekly Limits Will Rise 25% Permanently on September 14
ClaudeDevs says Anthropic will permanently raise standard Claude Code weekly limits by 25% starting September 14, 2026 for Pro, Max, Team, and seat-based Enterprise plans, with the current 50% increase in place until then. As of September 1, 2026, the day after the earlier promotion's documented expiry, the announcement still rests on that post alone: no Anthropic-owned page mentions September 14 or a permanent 25% increase.
OpenAI Plans to End Direct Cursor Model Access on November 12
OpenAI says it intends to wind down the contract that gives Cursor direct access to OpenAI models after Cursor's acquisition by SpaceX. The proposed shutoff date is November 12, 2026, but OpenAI says the final termination date is not yet confirmed. During the transition, users can consider an OpenAI API key for supported local Chat and Agent requests, the Codex IDE extension, or a compatible gateway; those options do not cover Cursor Tab, Auto, Cloud Agents, Background Agents, Automations, the CLI, API, or SDK.
ChatGPT Business Premium Seats Are Live: 5x More Usage and No Five-Hour Limit
OpenAI has made Premium seats available on ChatGPT Business. Premium seats cost $100 per user per month when billed annually or $125 monthly, provide 5x more usage than Standard seats, remove the five-hour usage limit, and can be mixed with Standard seats in one workspace.
Claude Cowork Gets a Built-In Browser: Web Tasks Without an Extension
Anthropic added a built-in browser to Claude Cowork on the desktop app. Claude can open webpages in a separate side-panel browser, read pages, click, type, and fill forms without using the user's own tabs or browser extension. The rollout covers Pro, Max, and Team plans, with Enterprise admin controls available first.
Claude Makes Enterprise-Managed Auth for MCP Connectors Generally Available
Anthropic says enterprise-managed auth for MCP connectors is now generally available. Claude Team and Enterprise admins can centralize authorization through their identity provider, while users receive connector access automatically without individual OAuth consent flows.
OpenAI Brings GPT-5.6 Model Family to Kiro for Spec-Driven Coding
OpenAI says the GPT-5.6 model family, including Sol, Terra, and Luna, is now available in Kiro. The OpenAI-AWS update targets structured, long-running software work and reports roughly an 82% cost reduction per successful Terminal-Bench 2.1 task for GPT-5.6 Terra in Kiro's spec-driven environment.
ChatGPT Sites Adds Teammate Editors: Collaborate on the Same Project and Publish Together
OpenAI added teammate editing to ChatGPT Sites. A Site owner can give an active member of the same ChatGPT workspace Can edit access; editors can update and save the Site, then publish later versions to the same URL after the owner’s first publish. Ownership, access, URL, secrets, and custom-domain controls remain with the owner.
ChatGPT Voice Can Start and Steer Codex Tasks on Desktop, With Mobile Remote Access
ChatGPT Voice now provides a hands-free way to start, monitor, and steer Codex work. OpenAI says Voice can coordinate Codex tasks in the ChatGPT desktop app, while mobile access is available through Remote on iOS after pairing an iPhone with a desktop host. Voice conversations use the Codex task’s usage budget and require a new chat or task to begin in voice mode.
Claude Code Remote Control Can Start Sessions From Your Phone
As of August 2026, a machine running claude remote-control appears as a device card at the top of the Code tab in the Claude app: tap it, pick a directory, and a session starts on that machine. Anthropic's Week 34 digest also took Remote Control out of research preview. Code and files stay local.
OpenAI Adds API-Key Spend Dashboards and Hard Limits
OpenAI's API platform now lets teams group Usage and Costs data by API key and set monthly organization or project spend limits. The dashboard feature helps identify which apps and workloads drive spend, while a hard limit can stop affected API traffic with a documented 429 error after the cap is reached.
Claude Security Brings Mythos 5 Scans to Enterprise Customers
Anthropic says Claude Security scans now run on Claude Mythos 5 for Claude Enterprise customers. The public-beta product scans connected codebases, returns CWE, confidence, severity, and suggested-fix details, and opens approved fixes in Claude Code on the web without exposing the Mythos model directly.
Ox Alpha Was Z.ai's GLM-5.3-Flash, and the Free Week Is Over
Ox Alpha was Z.ai's GLM-5.3-Flash. OpenRouter's model page now names the developer, the stealth listing serves no providers, and OpenCode has dropped Ox Alpha Free. The named model lists at $0.15 per 1M input tokens and $0.50 output, halved to $0.075 and $0.25 until September 9, 2026.
Claude Platform Makes Computer Use, Browser Use, Skills, and Files Generally Available
Anthropic says computer use, browser use, the Skills API, and the Files API are now generally available on the Claude Platform, combining multi-action software control with versioned skills and reusable files for production agents.
OpenAI Adds Transparent Backgrounds to GPT-Image-2 in API Preview
OpenAI added transparent-background output in preview for gpt-image-2 and gpt-image-2-2026-04-21 across the Images API and Responses API image-generation tool, with PNG or WebP output required.
Claude Managed Agents Add Memory Stores, Domain Controls, and a Redesigned Console
Anthropic's Claude Managed Agents updates let self-hosted sandbox sessions attach memory stores, restrict web_search and web_fetch with allowed_domains or blocked_domains, and inspect multi-agent sessions in a redesigned Claude Console viewer.
Cursor Cloud Agents Add Event Triggers, Long-Lived Goals, and Isolated Subagents
Cursor says Cloud Agents can now pick up work from events, keep working toward a long-lived goal, monitor pull requests, watch Slack threads, run scheduled tasks, and launch subagents in isolated virtual machines. The same update adds skill-based Custom Modes and less disruptive steering while an agent is working.
Claude Can Now Send Gmail Emails and Manage Google Drive Files
Anthropic's Claude can now send and reply to Gmail messages and manage Google Drive files from the connectors menu. The official announcement says the update is available on paid plans, while Anthropic's current help documentation details approval prompts, supported actions, admin controls, and important data-access limits.
Codex Opens GPT-5.6 Sol's 1M-Token Context to ChatGPT Accounts
GPT-5.6 Sol's 1M-token context window in Codex is now available for usage through ChatGPT accounts, not only API keys, according to OpenAI developer Tibo Sottiaux. The announcement also repeats a warning that Codex's default context length is tuned for performance and cost.
OpenAI's GPT-5.6 Builder's Guide Shows How to Make Agents More Efficient
OpenAI's GPT-5.6 builder's guide lays out a Responses API architecture for longer-running agents: persist reasoning, compact context, delegate work across agents, and move deterministic tool processing into code. OpenAI reports that these patterns raised GPT-5.6 Sol's ARC-AGI-3 score from 13.3% to 38.3% while using roughly 6x fewer output tokens.
Claude Code Desktop Adds Auto-Continue After Usage Limits
Claude Code now continues your session automatically when a claude.ai usage limit resets. Anthropic's changelog documents the behavior in version 2.1.234 as on by default, with an opt-out in /config named 'Continue automatically at usage limit'. It resumes work after a reset; it does not raise or remove the limit.
Cursor Welcomes Firetiger to Connect Coding Agents to Production
Cursor says the Firetiger team is joining Cursor to bring production-operation agents closer to coding agents. Firetiger's agents monitor rollouts, catch regressions, investigate incidents, and pass their findings back to coding agents. The announcement points to a longer-term workflow, not an immediate Cursor plan or feature change.
ChatGPT Adds Interactive Quizzes and Restaurant Reservation Search
OpenAI has added interactive quizzes to ChatGPT on web and mobile for consumer and Edu plans, while restaurant reservation search is rolling out across ChatGPT plans on mobile, web, and desktop. ChatGPT can use your topic, location, date, party size, and preferences to help with each workflow.
Cursor Is Now Part of SpaceX
Cursor says its acquisition by SpaceX has officially closed. The Cursor team will join SpaceXAI, with the companies aiming to combine SpaceX's computing capacity and Cursor's product experience to build stronger, more economical models and make them useful in products such as Cursor and Grok.
OpenAI Launches Computer History for ChatGPT and Codex on Mac
OpenAI is rolling out Computer History in the ChatGPT desktop app for macOS. When users opt in, ChatGPT and Codex can use recent interaction events to build local memories and a timeline, answer questions about past work, and suggest skills or automations. The feature is off by default and includes app and website permissions, pause and delete controls, and a 48-hour temporary event-file window.
Claude in Chrome Sessions Now Continue Across Devices
Anthropic says Claude in Chrome sessions now carry over to desktop, web, and mobile. Conversations are saved to the user's account, while skills and connectors can work from the browser; Claude's current Chrome page lists the extension as available on all paid plans.
Cursor Cloud Agents Start Up to 3x Faster With Builds
Cursor says Cloud Agents can start up to 3x faster with Builds, ready-to-use copies of development environments prepared in the background. Builds keep agents on the latest successful environment, expose logs and version history in the dashboard, and are now the default path for every Cloud Agent environment.
ChatGPT Desktop App Arrives on Linux in Preview
OpenAI is previewing the ChatGPT desktop app for Linux. The app brings ChatGPT, ChatGPT Work, and Codex to supported Linux systems, with official posts listing Ubuntu 24.04 and 26.04, Debian 13, and Fedora 43 and 44, plus .deb and .rpm packages for x64 and ARM64.
Codex Can Import Workflows From Other AI Agents
OpenAI now lets the ChatGPT desktop app and Codex CLI import supported setup and recent work from other agents. The desktop app can import from Claude Code, Claude Cowork, and Cursor, while Codex CLI supports Claude Code and Cursor, with automatic updates and import history available in the desktop app.
Grok 4.6 Lands in Cursor With a One-Week 2x Usage Window
SpaceXAI released Grok 4.6 on August 12, focused on long-running agents and visual work. It is live in Cursor and Grok Build with 2x included usage for the first week, and in the API plus OpenRouter, Vercel, and Cloudflare. Pricing starts at $2 per million input tokens and $6 per million output tokens.
OpenAI Expands Daybreak With GPT-5.6-Cyber
OpenAI expanded its Daybreak cybersecurity program with Blue and Red access tiers and introduced GPT-5.6-Cyber, a purpose-trained model for authorized vulnerability research, exploit validation, and security testing. Access is limited to approved defenders and organizations.
OpenAI Resets ChatGPT Work And Codex Limits For Paid Users
OpenAI executive Tibo announced usage resets for paid ChatGPT Work and Codex users on August 8 and August 29, 2026, then said the five-hour limit would return for Plus accounts across both products on August 26. The approved posts do not publish a numeric allowance, a new API billing rule, or details beyond that plan and product scope.
OpenAI Brings Codex Security Review to GitHub Pull Requests
Codex Security Review is OpenAI’s research-preview workflow for deeper security analysis of GitHub pull requests. It uses the diff, repository context, and optional threat-model guidance, then reports actionable findings in the pull request and a fuller report in Codex. Enterprise, Business, Edu, and Pro users can configure it; Plus is excluded.
Claude Code Will Make Auto Mode the Default on August 14
Anthropic says Claude Code will make auto mode the default for new sessions on Pro, Max, and Team plans starting August 14, 2026. The mode routes tool calls through a safety classifier, keeps manual approval available, and no longer charges those plans for classifier overhead.
Claude Code Sessions Can Now Message Each Other
Claude Code lets independent sessions discover and message one another, with controls for holding, refusing, or approving incoming messages. As of August 2026, sessions can also start conversations with sessions on other machines or Claude Code on the web, and native Windows is supported; the August 7 launch allowed only replies across machines and covered macOS and Linux.
ChatGPT Expands GPT-5.6 Luna Access and Adds a Reasoning Slider
OpenAI is making GPT-5.6 Sol the single Chat experience for Plus and Pro users, adding a reasoning-effort slider across web, mobile, and desktop. Free and Go users are getting GPT-5.6 Luna as the default model, unlimited text chats, and a Think button for harder questions.
Claude Fable 5 Reduces Biology Fallbacks by About 85%
Anthropic says an update to Claude Fable 5's biology safeguards reduced biology-related fallbacks by about 85% in testing. Fable 5 can now handle a wider range of everyday health and educational questions, while dual-use professional biology and drug-development requests remain restricted.
Agent Plugins: An Open Standard for Skills and MCP
OpenAI Developers introduced Agent Plugins, an open, vendor-neutral package format for sharing Agent Skills and MCP server configurations across compatible agent clients.
Cursor Router: Auto Balance, Auto Intelligence, and Cost Modes
Cursor Router is the routing system behind Auto, and Cursor documents it as available only on Teams and Enterprise plans. Open the model picker, select Auto, and pick Cost, Balance, or Intelligence under Optimize For. Every mode bills at the list price of whichever model the request is routed to.
Cursor SDK Bridge Opens Agent Control to Rust, Go, and More
Cursor has open-sourced an SDK Bridge that exposes a stable sdk.v1 protocol for driving Cursor agents from Rust, Go, Java, and other languages. Adapters run a small local bridge and communicate over Connect RPCs, while the bridge handles the connection to Cursor's API.
Cursor Agents Can Now Act Across Google Workspace
Cursor says new Google Workspace plugins give its coding agents direct access to Gmail, Google Drive, and Google Calendar. The plugins can search, read, draft, send, create, and manage Workspace data from inside Cursor, and install from the Cursor Marketplace or the Customize page.
OpenAI Details GPT-Live’s Full-Duplex Voice Architecture
OpenAI says GPT-Live is a third-generation voice system that can listen and speak at the same time, keep media flowing while deeper reasoning and tool use run asynchronously, and power ChatGPT Voice today. The architecture is also intended to underpin an upcoming GPT-Live API.
Cursor Says Cloud Agents Use 20-30% Fewer Tokens
Cursor says its cloud agents are now 20-30% more token efficient, with runs that use computer use becoming 80% more efficient. The update credits improvements to MCP, skills, computer use, and the cloud development environment behind those workflows.
GPT-5.4 Left ChatGPT-Signed-In Codex on August 31, 2026
OpenAI said GPT-5.4 and GPT-5.4 mini would stop being available in Codex for users signed in with ChatGPT on August 31, 2026, and that date has now passed. The models remain available through the OpenAI API and Codex sessions authenticated with an API key, confirmed September 1, 2026. Recommended replacements: GPT-5.6 Terra and GPT-5.6 Luna.
MCP 2026-07-28 Moves to a Stateless Core as Claude Rolls Out Support
Anthropic says the MCP 2026-07-28 specification moves the Model Context Protocol from a bidirectional stateful design to a request/response model, adds versioned extensions for MCP Apps and Tasks, and aligns authorization with production OAuth 2.0 and OIDC deployments.
OpenAI Releases Codex Security CLI for Repository Scans and CI Checks
OpenAI says its open-source Codex Security CLI can scan repositories, track findings across runs, verify fixes, and add security checks to CI/CD. The beta CLI requires Codex Security access and is built for teams that want code-aware security review in the terminal.
Codex ImageGen Adds a Lightbox + Canvas Workflow for Image Editing on Desktop
OpenAI Developers announced a new ImageGen workflow in Codex: a lightbox viewer and a canvas-style editing surface designed for direct, point-and-edit changes (erase, annotate, place text) instead of long prompt rewrites.
OpenAI Cuts GPT-5.6 Prices and Renames Priority Processing to Fast Mode
OpenAI reduced GPT-5.6 Luna pricing by 80% and Terra by 20%, then announced temporary GPT-5.6 Sol API and credit pricing relief for the next three months. OpenAI also renamed Priority processing to Fast mode and updated its pricing guidance for the GPT-5.6 family.
Cursor Launches Cursor Start: ₹649/Month Plan for Developers in India
Cursor Start is an India-only plan at ₹649 per month, tax inclusive, billed monthly in INR. Cursor's help docs say it covers Grok 4.6, Grok 4.5, and Composer 2.5 in non-fast mode at a fixed medium effort level, excludes third-party models and on-demand spend, and pauses AI features when the monthly pool runs out.
Claude Code artifacts can now call MCP connectors for live, viewer-specific data
Claude Code artifacts can call MCP connectors each time someone views them, so a published page shows current data rather than a session snapshot. Available on Pro, Max, Team, and Enterprise plans, requiring Claude Code v2.1.209 or later. Connector-backed artifacts cannot be shared to a public link on any plan.
Claude for Teachers: free premium access for verified US K-12 educators
Anthropic is launching Claude for Teachers with free premium Claude capabilities for verified US K–12 educators, plus teaching skills and curriculum connections aligned to all 50 state standards.
OpenAI Announces the Codex Micro: a Work Louder kbd-1.0 Collaboration for Codex Workflows
OpenAI Developers highlighted the Codex Micro, a $230 Work Louder co-lab keyboard accessory with RGB agent-status keys and dedicated controls for common Codex actions.
Claude Code Desktop Adds an iOS Simulator Pane: Watch Claude Test Your App Live
Claude Code Desktop opens Apple's iOS Simulator in a pane beside your conversation when Claude builds or checks your app, taps through it, and reads the screen to verify its own changes. Public beta on macOS for Pro, Max, Team, and Enterprise plans; needs Claude Desktop v1.24012.0+ and Xcode 26.x, not Xcode 27.
Claude Code Ships Screen Reader Mode: Plain-Text TUI for VoiceOver and NVDA
Claude Code now has an opt-in screen reader mode that replaces boxes, spinners, and in-place redraws with labeled linear text that VoiceOver and NVDA read in order. Turn it on with the --ax-screen-reader flag, the CLAUDE_AX_SCREEN_READER env var, or the axScreenReader setting (v2.1.181+). Menus become numbered lists, a terminal bell signals when Claude needs you, and separate settings cover magnifiers, reduced motion, and colorblind themes.
Cursor Doubles Usage Limits on All Individual and Teams Plans
Cursor doubled the included usage pool for its own models, and staff confirmed in writing that it is permanent: 'The doubled pool stays.' The pool now covers three models -- Cursor Grok 4.6, Grok 4.5, and Composer 2.5. What expired on July 21, 2026 was a separate 50 percent launch discount on Grok 4.5.
Google Ships Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
Google released three Gemini models on July 21, 2026: Gemini 3.6 Flash, a coding and knowledge-work workhorse at $1.50/$7.50 per million tokens that uses 17% fewer output tokens; Gemini 3.5 Flash-Lite, a 350 tokens-per-second model at $0.30/$2.50 for high-throughput agents; and Gemini 3.5 Flash Cyber, a security-specialized model piloted with governments and trusted partners.
OpenAI’s GPT‑Live‑1 powers the new ChatGPT Voice experience (web search, memory, and multimodal chat)
OpenAI’s latest ChatGPT Voice rollout is powered by GPT‑Live‑1 for paid users and GPT‑Live‑1 mini for Free users, enabling simultaneous listening and speaking and adding support for web search, memory, and mixed text+image conversations in Voice.
OpenAI Introduces GPT-Red: An Internal Automated Red-Teaming Model for Prompt Injection
OpenAI published details on GPT-Red, an internal automated safety red-teaming model designed to find prompt injection vulnerabilities at scale and strengthen defenses before broader deployment.
Cursor Adds GPT-5.6 Sol, Terra, and Luna
Cursor says the GPT-5.6 model family (Sol, Terra, Luna) is now available in Cursor and selectable from the model picker, with a published CursorBench score for Sol.
Cursor Adds Side Chats: Durable Agent Threads You Can @-Mention Back Into the Main Conversation
Cursor introduced Side chats: separate, durable agent conversations that run alongside a main chat and can be @-mentioned to pull context back.
OpenAI Launches ChatGPT Work: A Codex-Sibling Agent for Long-Running Deliverables
OpenAI introduced ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6 that takes action across apps and files and stays on a project for hours to turn a goal into finished work. Work handles research and deliverables; Codex stays the dedicated software-development agent.
Claude Adds Reflect: A Monthly Recap and Usage Dashboard for How You Use Claude
Anthropic introduced Reflect, a beta dashboard in Claude's Settings that shows a monthly recap of when you use Claude most and what you worked on, with quiet hours and break nudges. It runs only when memory is on, covers Free, Pro, and Max but not Team or Enterprise, and skips incognito chats, health integrations, Cowork, and Claude Code.
Claude Cowork Reaches Web and Mobile for Paid Plans
Claude Cowork is now available on web and mobile in beta for paid plans, so sessions can follow your Claude account across desktop, browser, and phone while work continues in the cloud.
OpenAI adds GPT-Realtime-2.1-mini to the API with reasoning and tool use
GPT-Realtime-2.1-mini is a distilled reasoning model for realtime voice, with function calling, a 128,000-token context window, and text, audio, and image input. OpenAI's pricing page lists it at the same rates as GPT-Realtime-mini: $0.60/$2.40 per 1M text tokens and $10/$20 per 1M audio tokens.
Claude Code Artifacts Expand to Pro and Max Plans (Private by Default)
Anthropic's ClaudeDevs says Claude Code Artifacts are now available on Pro and Max plans. The Claude Code docs now list Pro/Max/Team/Enterprise as eligible, with Pro/Max artifacts remaining private to the individual user.
Anthropic raises Claude API rate limits and consolidates tiers into Start, Build, and Scale
Anthropic consolidated Claude Platform usage tiers into three -- Start, Build, and Scale -- and raised rate limits so Sonnet and Haiku match Opus at every tier. Tier placement is automatic, based on usage history rather than spend, but each tier still carries a monthly spend cap.
OpenAI introduces GeneBench-Pro, a research-level benchmark for agentic computational biology
On June 30, 2026, OpenAI announced GeneBench-Pro: a research-level benchmark meant to measure how well AI agents navigate messy biological data and make the judgment calls real computational biology depends on. OpenAI says GeneBench-Pro contains 129 questions and is open-sourcing 10 representative case studies as a public package on Hugging Face under the MIT License.
Claude Desktop for Linux Beta: Ubuntu and Debian, With Caveats
Anthropic shipped a beta of the Claude desktop app for Linux on Ubuntu 22.04+ and Debian 12+ (x86_64 or arm64), with Chat, Cowork, and Claude Code on all paid plans. The app does not self-update; updates arrive through apt, and as of August 2026 a directly installed .deb registers the repo itself. Computer Use and Dictation are missing.
Claude Science Beta: An AI Workbench for Reproducible Research
Anthropic launched Claude Science in public beta -- a research environment, not a model. It runs analyses, queries 60+ scientific databases, and traces every step from data wrangling to publication, with code, environment, and conversation provenance attached to each artifact. It runs on your own infrastructure (laptop, HPC, GPU clusters) and submits jobs over SSH to your own machines or HPC clusters, or through a Modal account. Available now on macOS and Linux for Pro, Max, Team, and Enterprise plans.
Claude Sonnet 5 Launch: Anthropic's Most Agentic Sonnet, Now the Default Tier
Anthropic launched Claude Sonnet 5 on June 30, 2026, calling it its most agentic Sonnet yet -- it plans, drives browsers and terminals, and runs autonomously. It is the default for Free and Pro, available across all plans, in Claude Code, and on the API as claude-sonnet-5. Anthropic later made its $2 per million input and $10 per million output token pricing permanent.
Cursor for iOS: Cloud Agents Go Mobile-First in Public Beta
Cursor shipped a native iOS app in public beta on all paid plans. It launches always-on cloud agents that run in isolated VMs with full dev environments, work asynchronously toward merge-ready PRs, and report back via Live Activities and push notifications. You can also remote-control agents on your computer, pick any frontier model, use voice and slash commands, review diffs and demos, leave follow-ups, and merge PRs from the phone. Composer 2.5 runs are 75% off in the app through July 5, 2026.
Codex Permission Profiles: Least-Privilege Controls for Local Agent Work
OpenAI shipped Codex permission profiles in beta -- reusable, inheritable policies that replace the coarse sandbox_mode/sandbox_workspace_write combo. A profile binds OS-enforced filesystem read/write/deny rules (down to **/*.env) to per-domain network and Unix-socket rules. Enterprise admins get fail-closed allowlists via requirements.toml. Profiles govern local sandboxed command execution only, not MCP servers, app connectors, browser, or cloud.
Claude Code Adds Artifacts: Live, Shareable Pages for PR Walkthroughs and Dashboards
Anthropic introduced Artifacts in Claude Code, letting Team and Enterprise orgs turn an in-progress Claude Code session into a live web page that updates as the session progresses and can be shared privately within the organization.
OpenAI Previews GPT-5.6: Sol, Terra, and Luna in Limited Preview
OpenAI announced a limited preview of the GPT-5.6 family: Sol, a next-generation frontier flagship OpenAI calls a step function better than GPT-5.5; Terra, a balanced model competitive with GPT-5.5 at 2x lower cost; and Luna, its most cost-efficient model. Access starts with trusted partners in Codex and the API.
OpenAI Ships a New GPT-5.5 Instant in ChatGPT: Better Intent, Constraints, and Shopping/Local Recs
OpenAI says a new version of GPT-5.5 Instant is rolling out in ChatGPT with better intent understanding, more reliable handling of complex constraints, and improved shopping and local recommendations. Per OpenAI, it reaches paid users first and free users the next day. GPT-5.5 Instant is ChatGPT's default for logged-in users.
You Can Now Delegate Tasks to Cursor From Inside Notion
Notion used the Cursor SDK to embed coding agents directly in its workspace. You can now tag Cursor in a doc, mention it in a thread, or assign it a database issue, and Cursor plans, builds, tests, verifies its own work, and opens a PR. Notion says it built the integration in a few weeks on the Cursor SDK.
Claude Design's `/design-sync` Makes Claude Design and Claude Code a Two-Way Workflow
Anthropic's `/design-sync` pulls your design system into Claude Design so everything Claude builds starts from your real components, and keeps work synced as you move between Claude Design and Claude Code. You can start in either surface, hand a finished design off to Claude Code, and continue from existing work instead of a screenshot.
OpenAI Codex Adds Record & Replay: Turn a Demonstrated Mac Workflow Into a Reusable Skill
OpenAI shipped Record & Replay in Codex app 26.616, a macOS feature that turns a workflow you demonstrate into a reusable skill. It builds on Computer Use, which you or your administrator must enable, and is unavailable at launch in the European Economic Area, the United Kingdom, and Switzerland.
Cursor Origin Enters Early Beta: Code Hosting, Pull Requests, and GitHub Sync
Cursor's Origin code-hosting platform is now rolling out in early beta to paid plans, with hosted repositories, pull requests, code browsing, GitHub sync, and agents in every repo.
Anthropic Abruptly Suspends Fable 5 and Mythos 5 Access After US Government Directive
Anthropic says a US government export control directive ordered it to suspend all access to Claude Fable 5 and Mythos 5 by any foreign national, inside or outside the US. To comply, Anthropic is disabling both models for all customers. It says access to every other Anthropic model is unaffected, and that it is working to restore Fable 5 and Mythos 5 as soon as possible.
OpenAI: Responses API web search can now return image results
OpenAI added image results to the Responses API web_search tool, letting apps retrieve web-grounded visuals (with source links) alongside regular text results.
Cursor Bugbot gets faster and cheaper, adds /review command + incremental review
Cursor's June 10, 2026 update claims Bugbot PR reviews now finish ~3x faster (about 90s average vs ~5 minutes), cost ~22% less per run, and find ~10% more bugs per review. Cursor also added a /review command so you can run Bugbot and Security Review before pushing, plus an option to review only what changed since the last review.
ChatGPT 'Dreaming': OpenAI's New Memory Architecture Curates What It Remembers in the Background
OpenAI rolled out a more capable, compute-efficient ChatGPT memory architecture built on 'dreaming' -- a background process that curates memories by referencing chat history without prompting. It carries context forward better, follows preferences across conversations, and updates memories as time passes. Plus and Pro users in the US first, with Free and international users following.
Claude Fable 5 and Mythos 5: Mythos-Class Capability Goes General, With Caveats
Anthropic launched Claude Fable 5, a Mythos-class model made safe for general use and available today as claude-fable-5, plus Claude Mythos 5 for vetted cyberdefenders via Project Glasswing. Pricing is $10 per million input and $50 per million output tokens, with free subscription access ending June 23 and a mandatory 30-day data-retention policy on all Mythos-class traffic.
Codex for Every Role: Role-Specific Plugins, Codex Sites, and Annotations Beyond Code
OpenAI is pushing Codex past software development with three releases: six role-specific plugins bundling 62 apps and 110 skills, Codex Sites that turn analysis into shareable hosted web apps in preview for business and enterprise, and annotations that now refine documents, spreadsheets, and presentations -- not just code and websites.
Codex Build iOS Apps Plugin: Mirror the Simulator in the Browser and Hot-Reload SwiftUI Previews
OpenAI's Build iOS Apps plugin lets Codex mirror the iOS Simulator in the in-app browser and hot-reload package-backed SwiftUI previews without leaving Codex. It packages Swift and iOS workflows -- designing App Intents and Shortcuts, building and refactoring SwiftUI, auditing performance, and debugging on simulators through XcodeBuildMCP-backed flows. The plugin is open source in OpenAI's plugins repo.
Cursor Shared Canvases: Publish an Agent Canvas and Share It With Your Team via URL
Cursor added shared canvases -- you can now share a canvas from Cursor with your team by generating a link to a live snapshot that teammates open in the browser. Recipients view it read-only in the Cursor Dashboard, so you distribute a working dashboard or report instead of a full chat thread. Shared canvases are available on Pro, Teams, and Enterprise plans.
Claude Platform's 'ant' CLI Brings the Full Claude API to Your Terminal
Anthropic's Claude Platform documents 'ant', a command-line tool that exposes every Claude API resource as a subcommand. It sends Messages requests, browses responses, version-controls agents and environments, and runs a self-hosted Managed Agents worker, with Claude Code able to drive it natively.
Cursor 3.5 brings Automations into the Agents Window (plus multi-repo and no-repo automations)
Cursor 3.5 moves Automations into the Agents Window, adds multi-repo and no-repo automations, and introduces five new no-repo templates (with a 7-day 50% promo on agent runs for new automations).
Codex Adds Windows Computer Use + ChatGPT Mobile Windows Connections for On-the-Go Steering
OpenAI says Codex can now use Computer use on Windows to test apps, debug flows, and review work on your Windows machine, and that Codex in the ChatGPT mobile app can connect to Windows machines so you can steer tasks from your phone.
Claude Code adds dynamic workflows (research preview) for large parallel agent runs
Dynamic workflows in Claude Code let Claude write orchestration scripts, fan out work across tens to hundreds of parallel subagents, verify results, and resume long-running jobs.
Claude Opus 4.8 Fast Mode: 2.5x Faster Output Tokens in Research Preview
Anthropic launched Fast mode for Claude Opus 4.8 in research preview, promising 2.5x faster output token speeds with the same Opus-level intelligence. It is available now in Claude Code for developers with extra usage enabled, and on the Claude Platform API through an account manager or a waitlist form.
OpenAI's Secure MCP Tunnel: Connect Private MCP Servers Over Outbound-Only HTTPS
OpenAI's Secure MCP Tunnel connects private and on-prem MCP servers to ChatGPT, Codex, and the Responses API without opening inbound firewall ports. You need a tunnel_id, an API key with Tunnels Read plus Use, and -- separately -- ChatGPT developer-mode access. That permission split is the most common setup blocker.
Claude Code ships a security-guidance plugin for in-session vulnerability checks
Anthropic shipped an official security-guidance plugin for Claude Code. It runs automatic vulnerability checks while Claude edits files, at the end of each turn, and when Claude runs commits or pushes through its Bash tool.
Claude Agent SDK Gets a Monthly Credit on Paid Claude Plans Starting June 15, 2026
As of August 2026, the Claude Agent SDK monthly credit is not available: Anthropic paused the change on June 15, 2026, and Agent SDK, `claude -p`, and third-party app usage still draw from your subscription's usage limits. The May 26 announcement had promised Pro, Max, Team, and Enterprise plans $20 to $200 per month from June 15.
OpenAI Codex adds Locked computer use on Mac (keep Computer Use running after lock)
Codex can now keep using Mac apps after your screen locks. Locked computer use is a narrow, Codex-only unlock path with a short-lived authorization window and safeguards like relocking on local input.
Claude Managed Agents Add Self-Hosted Sandboxes (Public Beta) and MCP Tunnels (Research Preview)
Anthropic says Claude Managed Agents can now run tool execution in a sandbox you control (public beta) and connect to private MCP servers via MCP tunnels (research preview). The update targets enterprise security requirements by keeping execution and private services within an organization's perimeter.
Cursor Launches Composer 2.5: Better Long-Running Agent Work, New Pricing Tiers, and 2x Included Usage This Week
Cursor has released Composer 2.5, calling it its most powerful Composer model yet. Cursor says it's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. Cursor's launch post also says included usage is doubled for the first week. Cursor's blog post adds token pricing for Standard vs Fast modes.
Claude Code 2.1.142: `claude agents` Gains Session Flags, Fast Mode Defaults to Opus 4.7, MCP Tool Timeout Honored
Anthropic shipped Claude Code 2.1.142 on May 14, 2026. The release adds eight session-configuration flags to `claude agents` (`--add-dir`, `--settings`, `--mcp-config`, `--plugin-dir`, `--permission-mode`, `--model`, `--effort`, `--dangerously-skip-permissions`), flips fast mode's default model from Opus 4.6 to Opus 4.7, and fixes `MCP_TOOL_TIMEOUT` not raising the per-request fetch timeout for remote HTTP/SSE MCP servers -- a regression that capped tool calls at 60 seconds regardless of configuration.
Claude Code Weekly Limits +50%: The Promo Ended August 31, 2026
As of September 1, 2026, Anthropic's +50% Claude Code weekly-limits promo has ended. Its support article ran the window to August 31, 2026 at 11:59 PM PT after three extensions, and no fourth was published. A ClaudeDevs post says the 50% holds until a permanent 25% rise on September 14; no Anthropic-owned page carries that date.
Codex in the ChatGPT Mobile App: Run, Review, and Steer Codex from Your Phone
Yes, you can drive Codex from your phone. The ChatGPT mobile app on iOS and Android connects to a host running the ChatGPT desktop app on macOS or Windows, and from the phone you start work, review diffs and terminal output, and approve actions. Codex still executes on the host, which must stay awake and online.
Codex Chrome Extension: How Codex Drives a Signed-In Browser for LinkedIn, Salesforce, Gmail, and Internal Tools
OpenAI's Codex Chrome extension lets the agent use Chrome for browser tasks that need signed-in state -- LinkedIn, Salesforce, Gmail, internal tools. Available in the Codex app in all regions except EU and UK at launch. Setup is Codex > Plugins > add Chrome > install extension > approve permissions. Invoke with @Chrome. By default Codex asks before each new website; allowlist/blocklist and elevated-risk options live in Computer Use settings.
Codex Hooks and Programmatic Access Tokens: Setup, Trust Model, and What Actually Runs Today
Codex access tokens are ChatGPT Business and Enterprise workspace credentials for non-interactive Codex CLI runs. Create one at chatgpt.com/admin/access-tokens, then authenticate with CODEX_ACCESS_TOKEN or codex login --with-access-token. Hooks are the in-session extensibility framework: eleven lifecycle events. As of August 2026, command and mcp_tool handlers execute; at launch only command handlers did.
Cursor Bugbot Adds Effort Levels: Default, High, and Custom (Usage-Based Billing Required)
Cursor's May 11, 2026 update gave Bugbot three effort levels -- Default, High, and Custom -- and moved Bugbot off its $40 per seat plan onto usage-based billing for Teams and Individual plans, starting at each customer's first renewal after June 8, 2026. As of August 2026, effort levels are available only on usage-based Bugbot plans.
Codex CLI 0.130.0 Adds `remote-control`, Richer Plugin Sharing Metadata, and Better App-Server Thread Paging
OpenAI shipped Codex CLI 0.130.0 in May 2026. The release adds a new `codex remote-control` command for starting a headless, remotely controllable app-server, improves app-server clients with paging options for large threads (unloaded/summary/full turn items), expands plugin sharing with link metadata and discoverability controls, adds Bedrock auth support for AWS console-login credentials from `aws login` profiles, and fixes several app-server/thread reliability issues.
Gemini Interactions API: Steps Schema, `response_format`, and a June 8, 2026 Legacy Sunset
Google is rolling out breaking changes to the Gemini v1beta Interactions API that replace the `outputs` array with a `steps` array, remove `response_mime_type` in favor of a polymorphic `response_format`, and introduce new streaming event types. For REST users, the new schema becomes the default on May 26, 2026, and legacy behavior is removed on June 8, 2026; older Python/JS SDKs (1.x) also break on June 8.
Claude Code 2.1.133: `worktree.baseRef` Default Returns to `origin/<default>`, MCP OAuth Proxy Honored Across the Whole Flow
Anthropic shipped Claude Code 2.1.133 on May 7, 2026. The headline is a worktree-base behavior change: a new `worktree.baseRef` setting (`fresh` | `head`) defaults to `fresh`, which moves `EnterWorktree`'s base back to `origin/<default>` after three days of branching from local `HEAD` (since 2.1.128 on May 4). The release also routes `HTTP(S)_PROXY` / `NO_PROXY` / mTLS through the entire MCP OAuth flow (discovery, dynamic client registration, token exchange, refresh), exposes effort level to hooks via `$CLAUDE_EFFORT`, adds Linux sandbox path overrides, and fixes a refresh-token race that was 401-ing parallel sessions.
Codex CLI 0.129.0 Adds Modal Vim Composer, Redesigned Resume/Fork Picker, and a `/hooks` Browser
OpenAI shipped Codex CLI 0.129.0 on May 7, 2026. The release brings modal Vim editing to the TUI composer via `/vim`, a redesigned resume/fork picker, a raw scrollback mode, workspace-aware `/diff`, a new `/hooks` browser with before/after compaction support, expanded plugin management with workspace sharing and share access controls, theme-aware status lines, and Codex Apps auth surfaced through Guardian. Plus a long bug-fix list across Linux/Windows sandboxes, MCP, and TUI input handling.
Cursor adds enterprise model controls, soft spend limits, and richer usage analytics
Cursor's May 4, 2026 update adds granular model/provider access controls for Enterprise admins, introduces soft spend limits with automated alerts, and expands usage analytics so admins can break consumption down by product surface (including Cloud Agents, Bugbot, and Security Review).
Warp Goes Open Source: AGPL Client, MIT UI Framework, and a New `settings.toml`
On April 27, 2026 (changelog v0.2026.04.27.15.32) Warp open-sourced its client at github.com/warpdotdev/warp under AGPL v3, with the `warpui` UI framework crates released under MIT. The same release adds a TOML settings file editable from the settings page or by asking Warp's agent. The server stays closed-source. OpenAI is the founding sponsor.
Codex CLI 0.128.0 Lands Persisted `/goal` Workflows: Ralph-Style Agents That Don't Stop Until Done
OpenAI shipped Codex CLI 0.128.0 in April 2026 with a new `/goal` system that keeps a goal alive across turns and runs the agent until it is achieved. The release adds app-server APIs and model tools for goals, runtime continuation, and TUI controls to create, pause, resume, and clear goals. Felipe Coury credits co-worker Eric Traut (the Pyright lead) for the design, and frames it as Codex's take on the Ralph loop pattern.
Cursor SDK Lands in Public Beta: Programmatic Agents in TypeScript with Local and Cloud Runtimes
Cursor launched the Cursor SDK in public beta on April 29, 2026, exposing the same agent runtime that powers Cursor desktop, CLI, and web behind a TypeScript package. `@cursor/sdk` lets you spawn agents against local files, Cursor-hosted VMs, or self-hosted workers, stream results, and bill on standard token-based pricing -- moving Cursor from an editor surface to a programmable platform.
Anthropic's Claude Code Post-Mortem: Three Engineering Missteps Behind the Spring 2026 Quality Decline
Anthropic published a post-mortem on April 23, 2026 explaining the Claude Code quality regression that ran from early March through mid-April: a March 4 default-effort downgrade from high to medium, a March 26 caching change that wiped reasoning history every turn, and an April 16 verbosity prompt that capped responses at 25 words between tool calls. All three were resolved by April 20, the API was unaffected, and Anthropic reset usage limits for all subscribers.
Cursor 3.2 Adds /multitask Async Subagents, Worktrees Polish, and Multi-Root Workspaces
Cursor 3.2 shipped on April 24, 2026 with three changes: a `/multitask` command that fans a request out to async subagents instead of queueing, an improved worktrees experience for background branch work, and multi-root workspaces for cross-repo sessions. As of September 2026 the last two do not combine -- Cursor documents worktrees as disabled inside multi-root workspaces -- and `/multitask` no longer appears anywhere in Cursor's documentation.
GPT-5.5 Is Here: State-of-the-Art Agentic Coding, 1M Context, and a New Pro Tier
OpenAI launched GPT-5.5 on April 23, 2026 -- its smartest model yet, with state-of-the-art scores on Terminal-Bench 2.0 (82.7%), GDPval (84.9%), and OSWorld-Verified (78.7%), GPT-5.4 per-token latency, and a new GPT-5.5 Pro tier for harder work. As of August 2026 it is generally available in the API at $5/M input and $30/M output, with a 1,050,000-token context window.
Claude Design Launches: Anthropic Labs Turns Opus 4.7 Into a Prototype, Deck, and Wireframe Surface
Anthropic launched Claude Design on April 17, 2026 -- a research preview from Anthropic Labs that turns a prompt, uploaded image, or codebase into polished prototypes, pitch decks, and mockups. Powered by Claude Opus 4.7 vision, it learns your team's design system, exports to Canva, PDF, PPTX, or HTML, and packages finished designs for Claude Code handoff.
OpenAI Codex Goes 'For Almost Everything': Mac Computer Use, Browser Comment Mode, and Thread Automations Explained
OpenAI shipped a major Codex update on April 16, 2026 that pushes the product past coding into general work. Three changes matter: Codex can now drive your Mac apps directly, an in-app browser captures both screenshots and DOM elements through 'comment mode', and Codex threads can run continuously to watch Slack, email, and PRs. Here is how each works, the workflows that justify each one, and where Codex now sits relative to Perplexity Personal Computer and Claude Code Routines.
Cursor Self-Documentation: New Subagent-Powered Help Reads Cursor's Own Docs in Real Time
Cursor shipped a self-documentation feature on April 17, 2026: when you ask Cursor about its own features, capabilities, or settings, it now spawns a subagent that fetches the current Cursor docs and updates before answering. The change closes the most annoying gap in AI coding tools -- the model's training cutoff lagging the product's release cadence -- and is a small but telling preview of where AI tool documentation is heading across the industry.
Claude Opus 4.7 Is Here: State-of-the-Art Coding, xhigh Effort, and a New Cyber Safeguards Tier
Anthropic launched Claude Opus 4.7 on April 16, 2026 -- a notable improvement on Opus 4.6 in advanced software engineering, with the same pricing, a new xhigh effort level, /ultrareview in Claude Code, higher-resolution vision, and the first deployment of cyber safeguards from the Mythos Preview track.
Inside Claude Code's Rebuilt Desktop: Parallel Agents, Drag-Drop Panes, Side Chat
Anthropic rebuilt the Claude Code desktop app on April 14, 2026 around parallel agent workflows: a multi-session sidebar, drag-and-drop panes, an in-app file editor, integrated terminal, side chat, three view modes, and SSH on macOS. Four months on the app also creates routines and local scheduled tasks, browses external sites, and controls your computer.
Claude Code Routines: Schedule, API, and GitHub-Trigger Your AI Agents
Claude Code Routines is Anthropic's new way to run saved Claude Code configurations automatically -- by schedule, API call, or GitHub event. Routines run on Anthropic's cloud infrastructure with a prompt, repo, and MCP connectors. Available in research preview on Pro, Max, Team, and Enterprise plans.
AI Tools Landscape: What Changed in Early 2026
Three shifts defined AI tooling in early 2026: MCP settled as the cross-tool standard, coding assistants grew past autocomplete into multi-file workflow partners, and narrowly autonomous agents reached production. MCP's tipping point was earlier than this page first said -- Visual Studio Code made MCP support generally available in June 2025.