Lovable Can Now Publish Apps Into Your Company's Microsoft Account. The Publishing Part Is Still in Preview.
Lovable can now publish apps into a company's Microsoft tenant with work logins. The publishing step is in public preview, so check what IT sees first.
Issue 12: GPT-6 and Opus 5.5 Cost Less as Agent Controls Tighten
OpenAI lowered GPT-6 API rates, Anthropic estimates lower Opus 5.5 costs, and GitHub and Cursor added new controls to coding-agent workflows.
You Can Now Chat With Lovable for Free. Building Still Costs Credits.
Lovable now lets you chat for free to plan, compare ideas, or question an existing app. Building, images, and video still spend your paid credits.
v0 Can Now Pull In Your Private npm Packages. Here's the Setting to Check First.
v0 now installs private npm packages using saved Vercel environment variable credentials. Mark the token sensitive or teammates can read it in plain text.
Issue 11: A Photo-Decoding Bug Breached OpenAI, With an Assist From Claude
Hacktron used Claude to reach OpenAI through a libheif flaw, while Anthropic merged Cowork and chat and GitHub rewrote Copilot in Rust.
Lovable Can Now Publish Apps Straight Into Salesforce. Only Half of Them Actually Move.
Lovable can now publish read-only dashboards as native Salesforce pages, but apps that write data still run through Lovable. Here's the access check.
Issue 10: Agents Gain Autonomy Faster Than Controls Improve
Cursor expanded agent autonomy, a public report and Anthropic tests exposed sandbox gaps, and OpenAI advised lighter Astra instructions.
Bolt Is Giving Pro Users 50 Times More Usage. The Payment Is Your Build Sessions.
Bolt's new Forge agent runs on open-source models and offers 50 times the usage through October 14, but opting in trains future AI models on your sessions.
Lovable's New Drafts Feature Keeps Your Live App Safe. Your Live Data Is a Different Story.
Lovable's new Drafts let you test design changes without touching your live app, but drafts still read and write your live database. Here's the check.
Issue 9: Astra Costs More as Agent Trust Gets Harder
GPT-6 Astra arrived at premium pricing, two agent trust gaps surfaced, and Claude Code's weekly allowance will soon shrink.
Bolt.new Now Lets You Click an Element to Change It, No Prompt Required
Bolt.new's new Visual Edits toolbar lets you click any element and change text, fonts, and colors without writing a prompt. Here's the token catch.
v0 Apps Can Now Call AI Models Without an API Key. Here's Who Pays When They Do.
v0 generated apps now reach AI features through Vercel's Gateway with no API key setup. Here's who gets billed and the access setting to double check.
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.
Bolt.new Now Lets You Queue Your Next Idea While It's Still Building
Bolt.new added prompt queueing, so you can type your next idea while a build runs instead of waiting for the spinner. Here's the one habit to watch.
Dactyl Turns a Sentence Into a Real Native App, No Xcode Needed. Check This Before You Trust It With Real Users.
A team from Deno launched Dactyl, an AI builder that writes real native iOS and Android apps in your browser. Here's what to verify 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.
Netlify's App-Building Agent Will Now Ask What You Actually Meant
Netlify Agent Runners can now ask clarifying questions before building, aiming to cut wasted credits and rebuilds on AI-generated apps.
Replit's New 'Free Mode' Still Needs a Paid Plan. Here's What It Actually Buys You.
Replit's Free Mode stops charging credits for chat and planning, powered by GPT-5.6 Luna. It ships on paid Core and Pro plans only, not the free tier.
Replit Adds a Pen Test That Attacks Your Live App, Not Just Your Code
Replit's new Level 3 scan pokes at your live app the way a hacker would, catching exposure bugs its code-reading scanner misses. Here's how to run it.
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.
Base44 Adds Branches, But Your Data Doesn't Follow
Base44 added Branches so you can test app changes without touching the live version, but your real data isn't branched, only the design is.
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.
Lovable Now Gives Every Published App an Automatic Security Page
Lovable adds a trust center to every published app, showing platform security controls automatically. Here's what it covers and what it leaves out.
GitHub Is Shutting Down Spark. Here's What to Export Before August 31.
GitHub is retiring its Spark app builder and pointing builders to Copilot in VS Code and the CLI instead. Here's the export deadline and what it signals.