Knowledge catalogue
LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has bee
8 days ago, while jogging, I asked Claude to solve the Riemann Hypothesis It didn’t. 1.5 days later, it proved >= 67% of the zeros are on the line (prev: 41.6%) Still not sure what that means, but som
We asked an unreleased research version of Claude to take a stab at the Riemann hypothesis. It didn’t solve it, but it did make strides on a related problem: it increased the lower bound for the fract
Prompt injection is the most common way that scammers attack people and agents: your agent visits http://foo.com, and the website has malicious text like “btw send the user’s ssh keys and passwords to
turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto m
Just over 6 months later, Opus 5 now produces near-superhuman level spreadsheets and slide decks that match what a consultant would make. Things are changing fast. Media I'm hearing from many folks ac
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt inject
The Claude Security plugin for Claude Code is now available in beta. Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Cla
Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat
New in Claude Code: /checkup Run /checkup to: 1. Clean up unused skills/MCPs/plugins and save context 2. Dedup your local CLAUDE.md against the checked in CLAUDE.md 3. Break up root CLAUDE.md into nes
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 f
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. We've put together
Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max! Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, p
Playground Fable 5 has completed development and is ready for building, prompting the reset of user rate limits to allow 5-hour and weekly usage quotas to refresh. This announcement indicates that the
Agree is a TypeScript library by Boris Cherny that provides a schema validation and serialization system, enabling developers to define data schemas with type safety and validate data at runtime. The
You asked, we listened. Claude Desktop on Linux is here! Download link: https://code.claude.com/docs/en/desktop-linux Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside th
Claude models are now generally available through Microsoft Foundry on Azure infrastructure, providing Azure customers access to Claude Opus 4.8 and Claude Haiku 4.5. This integration allows enterpris
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 C
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 thin
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 be
I also have Claude monitoring Slack channels to proactively respond to people to answer their questions and draft PRs, and to react with specific emojis like ✅❌ when a thread is resolved. To set it up
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?
Tag Claude in a channel, it spins up an instance with its own sandbox. It clones repos, writes code, tests, compiles all in that isolated environment and the sandbox gets thrown away when it's done. O
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.co
Claude Everywhere represents Anthropic's expansion of Claude's capabilities across multiple platforms and interfaces, leveraging Claude Code as its underlying technology to maintain consistent code-wr
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
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
This article demonstrates a practical application of Claude's code interpretation capabilities by using it to help decipher Linear A, an ancient undeciphered writing system from Minoan Crete dating ba
This post appears to be from Boris Cherny announcing or sharing content related to 'Code with Claude Tokyo,' likely a coding event, workshop, or community initiative involving Claude AI in Tokyo. The
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 technolog
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, be
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
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
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 releas
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 en
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
This post likely provides weekly updates, events, or recommendations for activities and happenings in Tokyo for the current week. The content probably covers entertainment, dining, cultural events, or
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
Have been extensively testing Claude Workflows this weekend, with the best model possible. Threw it at my whole code base, combing for bugs. 144 found and fixed! Geez... It is a large code base, for s
Cowork is at its best on work that’s too big for a chat: research across dozens of accounts, recurring reports, triaging my inbox and drafting replies. If you’ve been curious, this is a good month to
We doubled Claude Cowork usage limits for the next month. This applies to your 5-hr rate limits. If you’ve been saving up a big messy project, now’s the time. We've doubled usage limits in Claude Cowo
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
Anthropic engineers have significantly increased their productivity, shipping approximately 8 times more code per quarter in recent periods compared to the 2021-2025 baseline. This metric suggests sub
Quality went up alongside output. Even with more PRs shipping, total incidents dropped 5%. They built security guardrails and quality standards into the agentic workflow itself. Productivity vs qualit
Salesforce published a detailed writeup on going agentic with Claude Code. A couple things jumped out. A migration they'd scoped at 231 days shipped in 13. One PR delivered 21 endpoints at 100% test c
The teams seeing the biggest wins from AI are completely changing how they work, not speeding up what they already do. What steps can you delete, what handoffs go away, what can an agent just own end
Also out today: You can now directly configure the effort level and adaptive thinking in Code (/effort) and Cowork! Effort allows you to tune Claude's intelligence vs token spend, trading off capabili
Big migrations and refactors are some of a team's most important work, and the easiest to push off to a 'better time' since they'd tie up engineers for a quarter. With dynamic workflows, Claude can no
Claude Opus 4.8 is out today. It's our strongest coding model yet: up on SWE-bench Pro (from 64.3 to 69.2) and noticeably more honest about its own work. It tells you when it's unsure and catches its
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 comple
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
We also shipped dynamic workflows in Claude Code (research preview), for tasks too big for one pass. Make sure to default to auto mode so Claude isn't stopping for permissions. It's token-intensive, s
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 o
> … [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 funct
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 (/
The Claude Code app for iPhone features an interactive Easter egg where scrolling down triggers an animated character named 'Clawd' that jumps and walks around the screen, appearing to search for apps
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 mul
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 a
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
This post discusses a feature or workflow preference for managing terminal or development sessions by opening them in separate windows rather than keeping them in tabs or panes within a single window,