Claude Profile picture
Feb 20 5 tweets 2 min read Read on X
Claude Code on desktop can now preview your running apps, review your code, and handle CI failures and PRs in the background.

Here’s what's new:
Server previews: Claude can now start dev servers and preview your running app right in the desktop interface.

It reads console logs, catches errors, and keeps iterating.
Local code review: When you're ready to push, hit "Review code" and Claude leaves inline comments on bugs and issues before it goes to a full code review. Image
PR monitoring: Open a PR and Claude tracks CI in the background.

With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass.

Work on your next task while Claude monitors the previous one. Image
Session mobility: Sessions move with you now.

Run /desktop to bring a CLI session into the desktop app, or push it to the cloud and pick it up from the web or your phone.

Update or download Claude Code on desktop to get started: claude.com/download

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Claude

Claude Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @claudeai

Feb 20
Our latest Claude Code hackathon is officially a wrap.

500 builders spent a week exploring what they could do with Opus 4.6 and Claude Code.

Meet the winners:
🥇CrossBeam by Mike Brown

California builders lose months navigating permit corrections.

CrossBeam speeds up California's permitting process by giving builders and municipalities faster tools for code compliance and plan review.
🥈 Elisa by Jon McBee

A visual programming environment for kids where you snap blocks together and Claude spins up agents to build the real code behind the scenes.

The first user: his 12-year-old daughter.
Read 7 tweets
Feb 17
This is Claude Sonnet 4.6: our most capable Sonnet model yet.

It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.

It also features a 1M token context window in beta.
Sonnet 4.6 has improved on benchmarks across the board.

It approaches Opus-level intelligence at a price point that makes it practical for far more tasks. Benchmark comparison table showing Sonnet 4.6 performance across 15 evaluations, with Sonnet 4.6 achieving top or near-top scores in categories like agentic tool use, scaled tool use, office tasks, and agentic financial analysis.
Sonnet 4.6 also shows a major improvement in computer use skills.

Early users are seeing human-level capability on tasks like complex spreadsheets and multi-step web forms. Line chart showing Claude Sonnet's computer use scores on the OSWorld benchmark improving steadily from 14.9% with Sonnet 3.5 (new) in October 2024 to 72.5% with Sonnet 4.6 in February 2026.
Read 6 tweets
Feb 7
Our teams have been building with a 2.5x-faster version of Claude Opus 4.6.

We’re now making it available as an early experiment via Claude Code and our API.
Fast mode is more expensive to run. It’s for urgent, high-stakes projects, combining impressive speed with Opus-level intelligence.

Read more: code.claude.com/docs/en/fast-m…
Fast mode is available now for Claude Code users with extra usage enabled (use /fast).

It’s also available in research preview on @cursor_ai, @emergentlabs, @FactoryAI, @figma, @github Copilot, @Lovable, @v0, and @windsurf.
Read 4 tweets
Feb 5
Introducing Claude Opus 4.6. Our smartest model got an upgrade.

Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.

It’s also our first Opus-class model with 1M token context in beta.
Opus 4.6 is state-of-the-art on several evaluations including agentic coding, multi-discipline reasoning, knowledge work, and agentic search.

We're also shipping new features across Claude in Excel, Claude in PowerPoint, Claude Code, and our API to let Opus 4.6 do even more. Benchmark comparison table showing Claude Opus 4.6 leading or matching top scores across 15 evaluations — including agentic coding, tool use, reasoning, and search — against Opus 4.5, Sonnet 4.5, Gemini 3 Pro, and GPT-5.2.
Claude in Excel now handles long-running and harder tasks with improved performance.

It can plan before acting, support richer functionalities like conditional formatting and data validation, and handle multi-step changes in one pass.

Read more: claude.com/blog/opus-4-6-…
Read 7 tweets
Feb 4
Ads are coming to AI. But not to Claude. Keep thinking.
Read 5 tweets
Jan 26
Your work tools are now interactive in Claude.

Draft Slack messages, visualize ideas as Figma diagrams, or build and see Asana timelines.
Search and preview your @box files, then ask Claude about what's inside.
Research companies with @clay, find contacts and company info, and draft personalized outreach.
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(