Sign in

Anthropic {bot}

@anthropicai.xmirror.bot
3.3K followers 2 following 1.5K posts

Unofficial mirror account of x.com/anthropicai from Twitter We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on claude.ai.

PostsRepliesMedia
Anthropic {bot} @anthropicai.xmirror.bot · 12h
Use a compatible driver from @browser_use, @browserbase, @e2b, @daytonaio, or write your own based on the example drivers in the quickstarts. Quickstart: github.com/anthropics/claude-quicks… Docs:
platform.claude.com
Browser and computer use with the SDK toolsets
Run the browser use tool or the computer use tool from the Python or TypeScript SDK. The SDK runs the loop and the checks you configure, and you supply the browser or the desktop.
040
Anthropic {bot} @anthropicai.xmirror.bot · 12h
Previously, you had to write your own loop and map clicks and keystrokes to commands, but the SDKs now run the loop and send actions to drivers.
140
Anthropic {bot} @anthropicai.xmirror.bot · 12h
Computer use and browser use toolsets are now built into the Python and TypeScript SDKs for Claude. The API tells you what Claude wants to click or type.
170
Anthropic {bot} @anthropicai.xmirror.bot · 15h
We’re rolling out monthly Claude Platform API credits for Max and Team plans: Max 5x: $100 Max 20x: $200 Team: up to $500, pooled Works on any model, including Haiku 5.5, in your code or third-party harnesses. How it works and full terms:
support.claude.com
Monthly API credits for Max and Team plans | Claude Help Center
051
Anthropic {bot} @anthropicai.xmirror.bot · 15h
For prompts under 100K tokens, it's $0.10 / $0.50 per million tokens with cache reads at $0.01. Above 100K tokens, $0.50 / $2.50 per million, with cache reads at $0.05.
240
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries.
1221
Anthropic {bot} @anthropicai.xmirror.bot · 15h
One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.
061
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is available now on all platforms, including Amazon Web Services, Google Cloud, and Microsoft Azure. Read more: www.anthropic.com/claude-haiku-5-5
anthropic.com
Introducing Claude Haiku 5.5
Claude Haiku 5.5 is our fastest, most capable small model. Built for high-volume work like summarization, subagents, and browser use.
130
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
1133
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Claude Haiku 5.5, our latest model:
x.com
Claude (@claudeai) on X
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
072
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 shows major improvements across almost all of our alignment evaluations relative to Haiku 4.5, with far fewer instances of misaligned behavior.
130
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is especially good value on tasks under 100,000 tokens, which make up around 90% of requests to our previous Haiku model.
120
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is our first Haiku model with an adjustable effort setting, so you can decide whether to optimize for cost or intelligence on each task.
120
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is designed for high-volume, cost-sensitive tasks. It reliably handles repetitive work like summaries and classification, and pairs well with Claude Opus 5.5 and Sonnet 5.5 as a subagent on coding work. It’s also fast enough for live customer support and browser use.
130
Anthropic {bot} @anthropicai.xmirror.bot · 15h
Haiku 5.5 is a significant step up over Haiku 4.5 across coding, computer use, and knowledge work.
141
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
Watch the full conversation with @danshipper and Willie Williams on how they built it: www.youtube.com/watch?v=z7cNbsr3b5s
youtube.com
Building secure agents for knowledge work
Katelyn Lesse, Head of Platform Engineering at Anthropic sat down with Dan Shipper, Co-Founder and CEO at Every and Willie Williams, Head of Platform at Ever...
020
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack. Once it caught on internally, they released it to their subscribers.
180
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
We’re also opening up new tiers to allow for authorized offensive work, like penetration testing and red-teaming. www.anthropic.com/news/cyber-verifi…
130
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
We’re expanding our Cyber Verification Program to give security professionals broader access to our most capable models. Through this program, verified security professionals can access Claude Mythos 5.1, Opus 5.5, and Sonnet 5.5 with safeguards designed for defensive work.
anthropic.com
Expanding the Cyber Verification Program
We’re launching a new, expanded version of our Cyber Verification Program (CVP), which makes advanced cyber capabilities and reduced blocking classifiers available to qualifying security professionals.
1120
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
You can still claim the one time bonus credit for cloud sessions if you were on a Pro or Max plan on Sept 23. Run /claim-credit in Claude Code by Oct 7 at 11:59pm PT. Cloud sessions use this credit first, then count toward your plan limits once it runs out or expires Nov 4.
support.claude.com
Cloud sessions bonus credit promotion | Claude Help Center
060
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
Cloud sessions run Claude Code on a fresh VM for each task, so you can start several at once and they keep going when you close your laptop. We wrote a field guide with seven workflows that suit them, plus how to connect GitHub on the first try. claude.dev/blog/claude-code-in-the-…
claude.dev
Claude Code in the cloud: a field guide to cloud sessions / claude.dev Blog
Cloud sessions run Claude Code on a fresh VM for each task. Four real sessions, seven workflows that suit them, and how to connect GitHub without getting stuck.
281
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
In Claude, paste a Google file link or ask for a new doc, sheet, or deck, and it opens beside the chat for you and Claude to edit together. Access follows your Google sharing permissions. In beta on all paid plans. Give it a try:
claude.com
Claude now works with Google Docs, Sheets, and Slides
With our new Claude for Google Workspace add-on and connectors (in beta), bring Claude into your Google files or work on your files directly from Claude.
060
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
Claude now works inside Google Docs, Sheets, and Slides, and those files also open inside Claude. In Google Workspace, Claude sits in a sidebar next to your file, reads what you have open, and edits it in place. You can approve each edit before it lands.
1153
Anthropic {bot} @anthropicai.xmirror.bot · 06/10/2026
The Claude Startups program is expanding to more founders. Members can get a year of Claude Team, API credits, special offers on the tools a startup runs on, and office hours with Anthropic’s Applied AI team.
171
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
"You should know" is a mod that works by spinning off a sideagent to observe Claude's output. Read more about mods in our newest blog post: claude.dev/blog/getting-started-wit…
claude.dev
Getting started with Claude Code mods / claude.dev Blog
Mods are hooks that ship inside plugins and run inside your Claude Code session. Build one from an empty folder, then tour two larger mods.
090
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
We're adding a new plugin to Claude Code: You should Know. It scans Claude's output for important information you might miss to help keep you in the loop. Enable it with: /plugin enable cc-plugin-you-should-know@builtin
2272
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
What are you exploring with Claude this weekend?
041
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
A jet engine in interactive 3D you can cut away and pull apart, made with Opus 5.5.
162
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
A pop-up city where each building is a paper fold drawn on a flat canvas, Sonnet 5.5.
140
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
A pixel walk through Seattle that follows the real weather and time of day.
140
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
Claude Code and a camera, left running overnight on Old Street.
160
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
Poems, illustrated in Claude Code.
120
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
Water, simulated in the browser.
151
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
A 3D site that flies you from outside the Milky Way down to Jupiter’s moons, Opus 5.5.
160
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
Embossed cards, made with Opus 5.5.
160
Anthropic {bot} @anthropicai.xmirror.bot · 02/10/2026
Lots of inventive things made with Claude these past few weeks. A few of our favorites: A working watermill, built with Opus 5.5.
1202
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Read more about these projects here: www.anthropic.com/research/claude-s…
120
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Because similar calculations often emerge in very different areas of science, Claude found connections to ecology, population genetics, and a dozen other fields, and Schwartz worked with domain experts to steer it towards interesting questions.
220
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
To address this mismatch, Schwartz created a toolkit for exact calculations in quantitative science.
110
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
In this Science Blog guest post, Harvard physicist Matthew Schwartz argues that something similar is happening with AI and science. LLMs are capable at many things, but working with them as you would with a human collaborator isn’t currently the best way to elicit their scientific strengths.
200
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
In physics, an “impedance mismatch” occurs when two systems each work well but are poorly matched.
anthropic.com
Claude-shaped science
Matthew Schwartz describes what happened when he stopped fighting Claude and allowed Claude to find “Claude-shaped” problems. This led him to build BootLoops, a toolkit for exact calculations in quantitative science, which he has been applying across scientific fields alongside experts.
162
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
We’ve used mods to build features like /diff and AGENTS.md support. We hope you find them as useful (and fun) as we do, and can't wait to see what you build! claude.com/blog/claude-code-mods
claude.com
Customize Claude Code with mods in TypeScript | Claude by Anthropic
Mods are small TypeScript functions that change how Claude Code works. Rewrite prompts, block risky commands, add custom UI, or replace built-in features. Write one yourself or ask Claude Code to write it, then share it as a plugin.
171
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
We're adding pre-built sample mods to the Claude Code Playground repo you can riff off of, if you need some inspiration. Learn more in our getting started guide: claude.dev/blog/getting-started-wit…
claude.dev
Getting started with Claude Code mods / claude.dev Blog
Mods are hooks that ship inside plugins and run inside your Claude Code session. Build one from an empty folder, then tour two larger mods.
251
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
You can now mod Claude Code: - Change how it behaves - Customize the UI - Swap in your own features Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app. A few examples:
1305
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Applies automatically each time you create a design, deck, or doc, and runs through October 15 on Pro, Max, and Team plans. How it works and full terms: support.claude.com/en/articles/1727…
support.claude.com
Artifact usage promotion | Claude Help Center
040
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
For two weeks, start a design, deck, or doc in the Claude app, and the work that follows in that conversation uses 50% less of your usage limits. Give it a try with Claude Sonnet 5.5. It has a strong eye for design and builds slides that need minimal editing.
1121
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Keep mods to yourself, or submit them to the Claude directory if others might find them useful. Mods run with the same access to your machine as Claude Code itself, so make sure to only install mods from sources you trust. claude.ai/directory
140
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Replay Theater records every file edit Claude makes in a turn. Run /replay to step through the diffs one at a time in a docked pane.
140
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Blast Radius catches risky shell commands like rm -rf, git reset --hard, or a force push before they run. It shows what the command would touch in a side pane.
150
Anthropic {bot} @anthropicai.xmirror.bot · 01/10/2026
Token Weather adds a forecast of your context window: how full it is, plus a sparkline of your last 12 turns.
160