Boris Cherny

RT ClaudeDevs Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.

This is pretty epic

RT cat Tomorrow at 10am PT I'm hosting a live walkthrough of how we progressed from single-player Claude Code to multi-player Claude Tag. Then, we're going deep on how Claude Tag actually works. AI used to finish your sentence. Then, it wrote entire features. Now, Claude Tag can monitor your channels, do proactive work for you, the whole team can steer it, and it remembers what you told it last week. Register: https://www.anthropic.com/webinars/how-anthropic-works-with-claude-tag-in-slack

This is our first time telling the story of how we first built and launched Claude Code, starting with its origins in Anthropic safety research. So much more to do. We are 1% done.

RT ClaudeDevs http://x.com/i/article/2074204645845839872

Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max!

RT ClaudeDevs Now that Fable 5 is ready to build (again), we've reset everyone's 5-hour and weekly rate limits.

Agree

You asked, we listened. Claude Desktop on Linux is here! Download link: https://code.claude.com/docs/en/desktop-linux

In the next version of Claude Code: subagents run in the background by default, so you can keep talking to Claude while your subagents work If you want your agent to run in the foreground, just tell Claude

As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes: 1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship 2. Builder: quickly turns a prototype/idea into production-grade product/infra 3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance 4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit 5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS. A healthy team needs a mix of these, depending on the product: - A product that is new and pre-PMF needs people that are strong at 1+2+3 - A product that is growing and has found PMF needs 2+3+4 and some 5 - A product that has strong PMF needs 3+4+5 and some 2 Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?

Re I tag Claude many times a day to write PRs, address user feedback, investigate incidents, do data analyses, summarize information, etc. Use it as your company's search engine. "What's the status on X?" "Who owns this service?" It answers your questions instead of just returning links. It’s been a huge unlock for onboarding new teammates.

Re That's it. Point it at a channel, give it a task, and let it work. It's in beta on Slack today for Claude Enterprise and Team customers. More surfaces coming soon! Learn more: https://www.anthropic.com/news/introducing-claude-tag

Re Claude is really proactive with Claude Tag. You don’t need to prompt it to do work, it can do work proactively based on your instructions. It has excellent memory and access to your data, so it can behave differently per channel

Re We’ve worked hard to make it secure at every level. 1/ At the model training stage, 2/ the classifiers on top of our models and things like auto mode, 3/ we protect what Claude has access to (websites it can access and it can’t see the credential secrets it uses), and 4/ respecting channel/workspace boundaries

Re This is the start of Claude Everywhere. It’s Claude Code under the hood so it’s just as good at writing code. 65% of our product team’s new code is created by our internal version of Claude Tag

We're launching Claude Tag today. Tag Claude into Slack and it works in channel with you. It’s proactive, multiplayer, with its own identity and memory. But it’s not just a bot in Slack. Over the last few months, it’s totally changed how we use Claude

Cool way to use Claude Code: deciphering Linear A, a 3500 year old written language from Crete https://aiclambake.com/clamtakes/linear-a/ Hope this holds up in peer review! 🤞

I've been using Artifacts in Claude Code for everything: visual explanations of tricky code, system diagrams, quick previews of a few animation options, data analyses and dashboards I share with the team. They are a game changer for how I work with Claude. Can't wait to hear what you think!

RT Claude New in Claude Design: it stays on brand with your design system across projects, lets you edit directly on the canvas, syncs with Claude Code, and connects to more of the tools you already use.

RT ClaudeDevs /goooooal ⚽

Hello from Code with Claude Tokyo!!

RT Dario Amodei Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: https://darioamodei.com/post/policy-on-the-ai-exponential

Enjoy!

Fable 5 is the biggest step up I’ve felt in our models since Opus 4.5 back in November. After 4.5 came out I uninstalled my IDE when I realized that I’d been doing 100% of my coding in a terminal for a few weeks. With Fable, it’s felt like Claude has stepped up from being a coding agent to a thought and design partner in building the product. Fable has judgement, taste, and dimensionality in a way that previous models didn’t, leading me to trust it more with the most complex work. I think the first time I had this realization was when I asked Fable to debug something. It is the first model I have used that was so methodical and precise, taking measurements and adding logs then verifying that it truly fixed the issue before declaring victory. There’s nothing in claude code’s prompting telling the model to do that, it’s just part of its personality. It really has this “big model smell” that I haven’t felt before.

We talk a lot about how important it is to set up self-verification loops. Especially in the age of powerful models that can run for long periods of time, self-verification is a key ingredient that enables the model to run for much longer, delivering a result that is closer to what you intended, so you can do more without having to constantly check in on Claude as it works. @delba_oliveira gives a great breakdown of what that looks like and why it matters

RT Andrej Karpathy This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

Fable 5 is now available in Claude Code and Cowork Fable is the best model I have used for coding, by a wide margin. It is a big step up, enabling less prompts and steers, more efficient token use, better code quality, better tool use, more intelligent self-verification, longer running sessions, and higher trust & autonomy. Happy coding!

RT Aaron Levie If you thought AI progress was slowing down, well here's the immediate answer to that. Huge jump in capability across the board. This is going to deliver major improvement in agents across almost all knowledge work categories.

Just landed nested subagent support in Claude Code Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s release. Lmk what you think!

RT Anthony Morris ツ maximum intelligence

When we first demoed Claude Code internally, it got two reactions on Slack. A year after GA, @_catwu and I sat down to talk about what's changed: why I use auto mode instead of plan mode, how routines fix bugs before I see them, why I do most of my coding from my phone now, and where the product is going

Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for approval 2. Use dynamic workflows, to have Claude orchestrate hundreds/thousands of agents to get a task done 3. Use /goal or /loop, to nudge Claude to keep going until it’s done 4. Use Claude Code in the cloud, so you can close your laptop (easiest way is the desktop or mobile app) 5. Make sure Claude has a way to self-verify its work end to end: Claude in Chrome browser extension for web, iOS/Android sim MCP for mobile, a way to start the full web server or service for backend work

RT Anthropic Re Today, Anthropic engineers on average ship 8x as much code per quarter as they did compared to 2021-2025.

RT Anthropic Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we thought, and the implications deserve greater attention. https://www.anthropic.com/institute/recursive-self-improvement

RT Anthropic We've raised $65 billion in Series H funding at a $965 billion post-money valuation, led by @AltimeterCap, Dragoneer, @Greenoaks, and @sequoia. This investment will help us advance our research and expand our capacity to meet growing demand for Claude.

RT Sid Super excited to finally share Dynamic Workflows in Claude Code!! We built this a couple months ago, and it has slowly become a daily driver for a bunch of people at Anthropic. A few tips for getting the most out of it 🧵 https://x.com/ClaudeDevs/status/2060044853279617150?s=20

RT ClaudeDevs New in Claude Code (research preview): dynamic workflows. Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks. Use the word "workflow" in a prompt to get started.

RT ClaudeDevs We’ve been putting a lot of effort into making Claude Code more responsive & reliable. Here’s an update on everything we’ve done:

RT ClaudeDevs We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code. Available for all Claude Code users. Install from the plugin marketplace (/plugins).

RT Anthropic New on the Engineering Blog: The access and permissions we grant agents should evolve with their capabilities. In our own products, we set these parameters through sandboxing, which limits the scope of any potentially destructive actions. Read more: https://www.anthropic.com/engineering/how-we-contain-claude

> … [W]e keep finding things that are mysterious, even unsettling. We find structures that mirror results from human neuroscience. We find evidence of introspection. We find internal states that functionally mirror joy, satisfaction, fear, grief, and unease. I don’t know what that means, but I think it warrants ongoing discernment. > We need more of the world—religious communities, civil society, scholars, governments, and indeed all people of good will … to take this seriously, to look closely, and to push events in a better direction. We need informed critics who will tell the labs when we are failing. We need moral voices that the incentives cannot bend.

RT Daniel San Just found that if you scroll down in the Claude Code app on iPhone… Clawd starts jumping and walking around looking for apps to build

People often ask what my biggest tip is for getting the most out of Claude Code. These days my #1 tip is: use auto mode Auto mode means no more permission prompts. It is the key building block for multi-clauding: start a session, then while it runs, work on another session in parallel.

RT Anthony Morris ツ sometimes you just want to pop your sessions out into their own windows

RT Anthropic Last month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then, we and our partners have found more than ten thousand high- or critical-severity vulnerabilities in essential software.

Big fan of teaching more people the basics of using Claude Code in an accessible way. So much of the world has not yet used agents. There's a lot of opportunity to level the playing field and expand access.

RT Anthony Morris ツ btw you can move your side chats any where you like

In the next version of Claude Code: run /usage to see a breakdown of which Skills, Agents, MCPs, and Plugins are using your tokens CLI today, coming to Desktop next

RT Movez Microsoft Senior AI developer just showed how they build AI agents with Claude at Microsoft. 34-minutes. free. By Microsoft team Opus 4.7 + 1,400+ pre-built MCP tools plug Claude into agent → give it tools → ship to production worth more than any $500 vibe-coding course.

RT ClaudeDevs Computer use turns Claude into an agent that can operate real UIs. New blog post on making it reliable in production: getting click accuracy right, choosing thinking effort levels, keeping long sessions within context, and recording demonstrations Claude can replay: https://claude.com/blog/best-practices-for-computer-and-browser-use-with-claude

RT Andrej Karpathy Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

Hello from Code with Claude London!

RT Prime Intellect Automating AI research is the next major step in AI We let Claude Code (Opus 4.7) and Codex (GPT 5.5) run autonomously on the nanoGPT speedrun optimizer track using our idle compute. ~10k runs, ~14k H200 hours Opus now holds the record at 2930 steps vs the 2990 human baseline

RT Andrew Curran Mythos has cracked MacOS. It took five days.

RT ClaudeDevs Claude Code weekly limits are increasing 50%, now through July 13. Live now for all Pro, Max, Team, and seat-based Enterprise users.

The UK AISI found Mythos Preview is the first model to solve both their cyber ranges end-to-end. No model had ever solved the AISI’s “Cooling Tower” cyber range before. We're getting it to defenders as fast as we responsibly can. More to come on our Glasswing work soon.

RT ClaudeDevs How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipped recently: /goal.

The best way to level up from 1 agent => many agents. No more cycling between terminal tabs

Clawd + last year’s umeshu (after letting it sit for 12 months, it turned out delicious!)

RT ClaudeDevs We're co-hosting a couple of hackathons in San Francisco next week. Come build with Claude 👇

We have a few extra stickers from Code with Claude! Grab some if you want https://www.stickermule.com/give/5DCYpto

RT Thariq http://x.com/i/article/2052796100608974848

RT marisa Claude code conference mini vlog! 🤍@ClaudeDevs @claudeai somehow left with: - a conference tamagotchi - an 8 bit version of myself - 47 new ideas - a typewriter response from claude

RT ClaudeDevs That's a wrap on Code with Claude San Francisco! Clawd had an amazing time, and we hope you did too. Thanks to everyone who came out and everyone who tuned in 🧡

RT Alex Albert With the help of Claude Mythos Preview, the Firefox team fixed more security bugs in April than in the past 15 months combined.

RT BridgeMind Claude Code just stopped a DDoS attack on BridgeMind in under 10 minutes. 13 million requests per minute hitting our API. CPU pegged at 94%. Latency spiking to 60 seconds. Production was down. I opened Claude Opus 4.7 in Claude Code and said "fix this now." It identified the attack, scaled ECS from 2 to 8 tasks, tightened WAF rules from 300 to 100 req/IP, blocked the attack vector, and brought CPU down to 15%. Latency dropped from 60 seconds to 1.25 seconds. No DevOps team. No on-call engineer. Just one prompt. This is why I keep coming back to Claude Code.

RT Aakash Gupta Anthropic just shipped sleep into agents. When you sleep, your hippocampus replays the day's neural sequences to the cortex during 150-220 Hz bursts called sharp-wave ripples. The replay runs about 20x faster than the original experience. A 10-second sequence gets compressed to roughly 500 milliseconds. Wilson and McNaughton showed this in rats in 1994. You ran this algorithm last night on whatever you did yesterday, whether you wanted to or not. The replay does two things at once. It extracts statistical patterns: what mattered, what generalizes, which sequences predicted reward. And it reorganizes the memory trace from hippocampus-dependent storage into neocortex, which is why old memories survive hippocampal damage but recent ones don't. Disrupt sharp-wave ripples in a rat with optogenetics and the rat fails the next day's task. The replay is causal, not correlational. Most "agent memory" today is a search engine. Past sessions get embedded, you retrieve relevant chunks at the next call. That works for facts. It does not extract patterns and it does not reorganize the trace. Which is why agents plateau. The memory volume keeps growing while real capability flatlines. Dreaming reviews past sessions, extracts patterns, curates memories. That is the brain's actual three-step algorithm. They called it dreaming because dreaming is what the algorithm does, in roughly the same order, for roughly the same reason. Agents that dream between sessions will compound. The ones still running on raw context window will hit the same ceiling humans hit when they pull all-nighters.

RT NVIDIA Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Colossus 1. The future of AI runs on NVIDIA.

Hello from Code with Claude!

RT Claude We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.

RT ClaudeDevs Code with Claude is happening now! ▪︎ 9:00AM - Keynote ▪︎ 10:30AM - What's new in Claude Code ▪︎ 11:15AM - Building on Claude at GitHub scale ▪︎ 12:00PM - Get to production faster with Managed Agents All times PT. https://x.com/i/broadcasts/1qGoNegbnRNKv

See everyone tomorrow!!

RT ClaudeDevs In the last four Claude Code CLI releases, we’ve shipped 50+ stability and performance fixes. Faster resume, stable auth, lower memory, fewer hangs: 🧵

RT Adam Wolff After 2.1.117, you may notice that Claude doesn't call its Grep or Glob Tool anymore. YES!!! It only took four months. It's faster than ever and it's all Bash. It's so much harder to take things away than to add them. Enjoy.

Claude Code won a Webby! Thanks to all of our users and customers for the support and love, and for always giving us feedback so that we can continue making the product a little better every day. https://winners.webbyawards.com/2026/ai/ai-features-innovation/best-product-or-service/387497/claude-code

RT Amol Avasare For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected.

RT Claude In Cowork, Claude can now build live artifacts: dashboards and trackers connected to your apps and files. Open one any time and it refreshes with current data.

RT Felix Rieseberg Hi! I'm here with *another launch*, it just happens to be extremely niche, nerdy, and probably only for a handful of people. In the desktop app, Claude Cowork and Code now have a little Bluetooth API for makers & developers, allowing you to build hardware devices that interact with Claude. I, for instance, built a little desk pet that alerts me whenever Claude is waiting for permission.

RT ClaudeDevs We fixed a bug where rate limits on Claude subscriptions weren't properly adjusted for long context requests in Opus 4.7. We've reset 5-hour and weekly rate limits. Enjoy Opus 4.7!

RT Austin Ray Merry Claude-mas! Opus 4.7 in Claude Code is a monster. Very happy camper! https://www.anthropic.com/news/claude-opus-4-7

Opus 4.7 feels more intelligent, agentic, and precise than 4.6. It took a few days for me to learn how to work with it effectively, to fully take advantage of its new capabilities. Will post a few more tips throughout the day, starting with this blog post: https://claude.com/blog/best-practices-for-using-claude-opus-4-7-with-claude-code

RT ClaudeDevs For the developers building with Claude, a direct line from the team. Follow for changelogs, API releases, community updates, and deep dives.

RT ClaudeDevs ✻ Flibbertigibetting…

RT Jarred Sumner People have been asking for this for years. It wasn't clear how to make it performant enough to be shippable, until earlier today

Thanks @AcquiredFM for hosting me on Unplugged! Had a blast

We've been working on this for a while. Can't wait to hear what you think

brb trying this now

RT Noah Zweben Claude now supports dynamic looping. If you run /loop without passing an interval, Claude will dynamically schedule the next tick based on your task. It also may directly use the Monitor tool to bypass polling altogether /loop check CI on my PR Original tweet: https://x.com/noahzweben/status/2042670949003153647

RT Claude Claude for Word is now in beta. Draft, edit, and revise documents directly from the sidebar. Claude preserves your formatting, and edits appear as tracked changes. Available on Team and Enterprise plans. Original tweet: https://x.com/claudeai/status/2042670341915295865

1/3 Just got a nice DM from a big enterprise customer using Claude Code in one of the world's biggest codebases Here's how we made @-mentions 3x faster in large enterprise codebases 🧵2/3 After a few hours, I had a PR. The results were solid -- P99 got 3x faster after porting to TypeScript!3/3 The wins came from three places: 1. Pre-computing upfront in a clever way that doesn't block the main thread 2. Avoiding NAPI overhead for small result sets 3. Iteratively asking Claude to find perf improvements for faster file search

Claude Cowork, now generally available!

RT Claude Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform. Original tweet: https://x.com/claudeai/status/2041927687460024721

RT Amol Avasare Had a great chat with @lennysan on some of the fun stuff happening at the intersection of AI and growth! Thanks for having me on Lenny, had a blast :) https://open.spotify.com/episode/08QWCmKgDbMfpojknVW5Fa Original tweet: https://x.com/TheAmolAvasare/status/2041725306277654925

RT Noah Zweben /autofix-pr now lets you kick off autofix straight from the command line. After finishing up a PR, just run /autofix-pr. It sends your session to the cloud so the PR autofixer has full context to address CI failures and comments. Hugely win for my productivity. Original tweet: https://x.com/noahzweben/status/2041654973491245509

Mythos is very powerful, and should feel terrifying. I am proud of our approach to responsibly preview it with cyber defenders, rather than generally releasing it into the wild. Model card here: https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf

RT Anthropic Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. https://anthropic.com/glasswing Original tweet: https://x.com/AnthropicAI/status/2041578392852517128

RT Anthropic Re Our run-rate revenue has surpassed $30 billion, up from $9 billion at the end of 2025, as demand for Claude continues to accelerate. This partnership gives us the compute to keep pace. Read more: https://www.anthropic.com/news/google-broadcom-partnership-compute Original tweet: https://x.com/AnthropicAI/status/2041275563466502560

RT Anthropic We've signed an agreement with Google and Broadcom for multiple gigawatts of next-generation TPU capacity, coming online starting in 2027, to train and serve frontier Claude models. Original tweet: https://x.com/AnthropicAI/status/2041275561704931636

RT Noah Zweben Incredible to see @ForeverSolar using the Claude Agent SDK to drive permitting wins in the solar industry "Claude Agent SDK scored 97.5% on our benchmark—we couldn't break it...Other frameworks hit 20–60% at higher cost." https://claude.com/customers/freedom-forever Yay green energy! Original tweet: https://x.com/noahzweben/status/2040182670974660867