What AI Update Did You Miss Today?

Claude Code Adds a GitLab Merge Request Badge to the Footer

Claude Code now surfaces a live GitLab merge request badge in the footer and statusline, mirroring the GitHub pull-request badge that already existed. Developers on a GitLab remote with an authenticated `glab` CLI see the MR number (`!N`) along with its current state — draft, pending, or green — without leaving the terminal. The change closes a long-standing gap for teams whose primary git host is GitLab rather than GitHub.

Claude Code

Claude Code Lets You Open /permissions and /add-dir While Claude Is Working

Claude Code no longer forces users to wait for a turn to finish before adjusting settings. `/permissions` can now be opened mid-turn, with rule changes taking effect for the rest of the current turn, and `/add-dir` can add a working directory while Claude is actively running. Several other dialogs — including `/autocompact`, `/theme`, `/help`, `/config`, and `/advisor` — now open mid-turn in the fullscreen TUI as well.

Claude Code

Claude Code Fixes Permission Preview Leaks That Could Hide Commands From Approvers

Claude Code patched three related weaknesses in how permission previews — the summaries relayed to a remote approver before a tool runs — are secured and displayed. Credential masking could previously over-redact and hide the actual command, path, or destination from the person approving it, meaning an approver could unknowingly greenlight an action they couldn't fully see. A separate gap let previews relay to channel servers that hadn't been vetted by the inbound trust gate, and provider API tokens weren't always masked when directly followed by shell delimiters.

Claude Code

Grok 4.6 Now Available in GitHub Copilot

GitHub Copilot has added xAI's Grok 4.6 as a selectable model across eight surfaces, including VS Code, Visual Studio, Copilot CLI, the Copilot cloud agent, the Copilot app, JetBrains, Xcode, and Eclipse. This is a third-party model integration (Grok is built by xAI, not GitHub) tuned for agentic coding and long-horizon, multi-step reasoning tasks. It is available on Copilot Pro, Pro+, Max, Business, and Enterprise plans, billed at usage-based provider list pricing, though Business and Enterprise admins must explicitly enable it since the policy is off by default.

GitHub Copilot

7/10

Replit Launches Native MCP Server for ChatGPT, Claude, and Slack

Replit launched a native MCP (Model Context Protocol) server, allowing ChatGPT, Claude, Slack, and any compatible MCP client to connect directly to Replit. Users can now create, find, inspect, update, and publish Replit apps — or duplicate an existing app to edit — entirely from within their AI assistant's chat interface. The move turns Replit into a callable backend for other AI tools rather than a standalone destination, extending Replit's reach to wherever developers already work.

Replit

4.5/10

Figma: Text Wrap with Balance and Pretty

Figma introduced native text wrap controls that make text layers responsive across different screen sizes, adding two new settings: Balance, which distributes text evenly across lines, and Pretty, which prevents a single word from being stranded alone on the last line. Either option can be applied to a text layer, a text style, or an individual paragraph directly from text settings. The update mirrors the CSS text-wrap: balance and text-wrap: pretty properties, closing a long-requested gap between Figma's typography controls and how modern browsers actually render text.

Figma

4/10

V0: Ask V0 to Manage Your Other Chats

V0 can now list, inspect, create, and continue other chats directly when asked within a conversation — turning V0 into a lightweight orchestrator across a user's own workspace instead of confining each chat to itself. This meta-level capability lets users manage multiple in-progress projects conversationally rather than manually switching between chats in the sidebar.

3.5/10

Claude Code Turns Off Todo Tracking by Default on Newest Models

Claude Code 2.1.233 turns off its built-in todo and task-tracking tools by default when running on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models. The TaskCreate, TaskGet, TaskUpdate, TaskList, and TodoWrite tools, which power the visible checklist Claude Code shows while working through multi-step work, no longer load automatically on those models. Setting the CLAUDE_CODE_ENABLE_TODO_TOOLS=1 environment variable restores the old behavior. Anyone accustomed to watching Claude Code check off a running task list will notice its absence unless they opt back in.

Claude Code

3.5/10

Replit Workspace Skills: Sharing and Admin Controls

Replit extended its Agent Skills system so workspace members can create skills and share them with the whole team, not just use them individually. Shared skills start turned off for everyone else, and each teammate chooses which ones to enable. Administrators gained the ability to manage every skill across the workspace and mandate specific ones for all members, backed by a redesigned Skills Library that makes skills easier to discover and administer.

Replit

3.5/10

V0: Redesigned Sidebar with Project Grouping and Persistent Resizing

V0 rebuilt its sidebar to make navigating large numbers of chats and projects easier. Chats are now grouped by project and ordered by recent activity, the sidebar can be resized to a width that persists across sessions, and right-click context menus give quick access to chat and project actions. A new favicon badge signals when a chat has finished streaming or needs input, and archiving replaces permanent deletion so old chats can be recovered later.

V0: Deployment Popover Adds Live CI Checks and Contextual Fix Actions

V0's deployment popover now surfaces clickable commit, inspector, and site links, along with a live row showing CI check status as it runs. A new contextual action button intelligently switches between Review Code, Fix CI, and Fix Conflicts depending on the deployment's current state, cutting down on the number of steps needed to diagnose and resolve a broken deploy.

Claude Code Closes a Windows NTLM Credential-Leak Path

Claude Code 2.1.233 closes a Windows-specific path-validation gap that could leak NTLM credentials. Anthropic found that file paths written with the NT \??\ device prefix slipped past the tool's UNC path validation, meaning a crafted path could reach a remote share without triggering the permission checks meant to catch it. Because Windows automatically attempts NTLM authentication the moment a UNC-style path is touched, an attacker-controlled path could have coaxed a victim's machine into leaking its NTLM hash to a remote server. The fix brings the \??\ prefix spelling under the same validation as ordinary UNC paths.

Claude Code

Claude Code Desktop Adds an Auto-Continue Checkbox for Usage Limits

Anthropic's Claude Code developer account announced an auto-continue checkbox for the Claude Code desktop app on August 14, 2026. When enabled before or during a usage-limit stop, the option automatically resumes a session once the 5-hour or weekly usage window resets, instead of leaving the agent idle until someone manually re-prompts it. The feature targets long-running and overnight agentic work that previously stalled the moment a usage window ran out. It does not raise usage limits themselves, only automates the wait-and-resume step, and at launch it ships on the desktop app only.

Claude Code

Replit Adds One-Click Migration to Clerk Auth

Replit launched a guided, Agent-driven migration path that moves eligible apps from Replit Auth to Clerk Auth while preserving existing user accounts and data. Developers can trigger the migration by asking Agent directly or through the Users & Auth panel, and Agent handles moving account data before updating sign-in code so returning users retain access. The feature complements Replit's earlier rollout of enterprise SSO via Clerk, giving teams still on the original auth system a supported upgrade path.

Replit