Issue 8: Claude Gains Browser Autonomy as Copilot Keeps Chat History
Claude gained browser autonomy, GitHub made Copilot chat history persistent, and v0 moved AI usage onto builders’ Vercel accounts.
A Researcher Broke Claude Code's Default Auto Mode. Anthropic Calls It Working As Intended.
A researcher chained ordinary Claude Code steps into real code execution against Auto Mode. Anthropic closed the report as informative, not a bug.
OpenAI Is Bringing Back Codex's 5-Hour Cap for Plus Users. Pro Plans Stay Exempt.
OpenAI is reinstating a 5-hour usage cap on Codex and ChatGPT Work for Plus subscribers, reversing a six-week suspension. Pro plans are exempt for now.
GitHub Copilot Now Takes Requests From Slack. Here's Who Can Set It Off.
GitHub Copilot can now start a coding session from a Slack message and open a pull request while you're away. Check this setting first.
Issue 7: Agents Move Into Slack as OpenAI Slows Training
OpenAI paused reinforcement-learning work on near-release models. GitHub Copilot and Vercel Agent moved into Slack. App security gaps surfaced.
Claude Code Now Resumes Itself When Your Limit Resets. Anthropic Also Extended the Bigger Limits Again.
Claude Code auto-resumes sessions when your usage limit clears, and Anthropic extended its 50% capacity boost through August 31. Here's the opt-out.
Codex Can Now Fork a Session Instead of Restarting It, and Show You What It's Costing
OpenAI's Codex CLI adds session forking so you can branch a risky change safely, plus a cost meter that only some workspaces can see so far.
ChatGPT's New Computer History Lets Codex See What You Just Did. OpenAI Flags a Prompt Injection Risk.
OpenAI's Computer History gives Codex a timeline of your clicks and app activity for context. OpenAI's own docs say that also raises prompt injection risk.
Grok 4.6 Just Joined GitHub Copilot's Model Picker. Check the Price Before You Switch.
GitHub Copilot added xAI's Grok 4.6 for agentic coding tasks, billed at the provider's own token rate instead of a GitHub-negotiated price.
Issue 6: Connected Agent Workflows Move the Safety Check to the Boundaries
Six vendors joined the Agent Plugins standard as Claude Code connected sessions and platforms tightened boundaries around data, access, and environments.
Cursor's Cloud Agents Get Pre-Built Environments. Check Your Install Script Before August 17.
Cursor's new builds feature boots cloud agents up to 3x faster and becomes the default for everyone on August 17. One setup detail is worth checking first.
Cursor's Design Mode Now Takes Voice Commands and Lets You Queue Edits Without Waiting
Cursor's Design Mode now adds voice commands and faster targeting, so you can direct UI changes without leaving the running app.
GitHub Copilot's Agent Plugins Standard Packages a Skill Once for Every Client. Six Vendors Signed On.
GitHub Copilot's Agent Plugins standard packages a skill and MCP server into one file for VS Code, the CLI, and the app. Five more vendors co-maintain it.
GitHub Copilot for JetBrains Now Remembers You. Check This Before You Trust It.
GitHub Copilot for JetBrains adds memory across chat sessions and local Ollama models. Here's the scoping question to check before you rely on either.
Grok Bot Launched From a Cursor Domain. That's Not a Mistake.
Grok Bot's beta is bundled into Cursor's own paid plans because SpaceX's pending $60 billion Cursor deal is close to done. Here's what that means for you.
Claude Code Sessions Can Now Message Each Other. Here's What Decides If It Gets Through.
Claude Code sessions can now message each other automatically. Whether it needs your approval depends on which permission mode each session runs.
Claude Code Will Auto-Approve Most Commands by Default Starting August 14
Claude Code makes auto mode the default permission setting on August 14 for Pro, Max, and Team plans. Here's what still gets blocked and how to opt out.
Issue 5: Claude Code Makes Auto-Approve the Default After a Week of Patching Permission Bypasses
Claude Code makes auto-approve the default on August 14, days after patching two permission bypasses, while Cursor's usage page stops showing dollars.
OpenAI Codex Adds an Auto-Review Flag for Command Approvals. Here's What It Actually Does.
Codex 0.147.0 adds an approve for me flag that routes command approvals through automatic review. OpenAI hasn't published how that review decides.
Claude Code Patches Four More Permission Bypasses in Three Days
Claude Code 2.1.223 fixes a second Bash permission bypass, a hidden-command trick, and a workflow sandbox escape, days after its last patch.
Claude Code Patches a Bash Permission Bypass and Adds Credential Masking
Claude Code 2.1.221 fixes a zsh permission bypass in the Bash tool and adds credential masking for sandboxed commands. Here's what changed.
GitHub Copilot Automations Can Now Trigger From a Comment. Check One Setting First.
GitHub Copilot cloud agent automations can now trigger from a comment. One repository setting decides whether outside commenters can set them off too.
Cursor's Usage Page Now Shows Tokens, Not Dollars. Here's Where Your Real Spend Still Lives.
Cursor's Usage page now shows token counts instead of dollar figures for individual plans. Here's why, and where your actual bill still shows up.
Issue 4: Builder Platforms Start Setting Their Own Limits
OpenAI cut GPT-5.6 Luna's price 80%, Vercel added spend budgets to its AI Gateway, and Netlify tightened project privacy defaults this week.