Boris Cherny (@bcherny)

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)?

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 been solved, but not all. While models continue to improve, adversarial code review has been an incredibly powerful tool to catch many of these kinds of bugs. It can be as simple as a one line prompt - “use a dynamic workflow to adversarial test every edge case in an iOS simulator”, or use Claude’s built in /code-review (or /code-review low, /code-review medium, etc.)

@thsottiaux We are hiring if you would like to work at Anthropic! We don’t ban people for using harnesses with other models. Almost certainly it was a different account classifier that triggered. Looking into it, thanks for escalating.

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?

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

It's late 2024, a few days after I launched the first version of Claude Code (then called Claude CLI) to team dogfooding. I walked into the office and saw my coworker Robert with a terminal up on his computer, Claude CLI running and a red/green diff view on screen. I was surprised. This was back in the Sonnet 3.5 days, before the model was good at agentic coding. I had just given it a FileEdit tool the day before. Claude CLI was a prototype that I thought it wasn't useful for anything yet. But Robert was already starting to use it to write code & use git for him. I was still using the CLI as a note taker mostly, but I also started making it my go-to tool for using git as a result.

We just open sourced the code-simplifier agent we use on the Claude Code team. Try it: claude plugin install code-simplifier Or from within a session: /plugin marketplace update claude-plugins-official /plugin install code-simplifier Ask Claude to use the code simplifier agent at the end of a long coding session, or to clean up complex PRs. Let us know what you think!

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently. So, here goes.

When I created Claude Code as a side project back in September 2024, I had no idea it would grow to be what it is today. It is humbling to see how Claude Code has become a core dev tool for so many engineers, how enthusiastic the community is, and how people are using it for all sorts of things from coding, to devops, to research, to non-technical use cases. This technology is alien and magical, and it makes it so much easier for people to build and create. Increasingly, code is no longer the bottleneck. A year ago, Claude struggled to generate bash commands without escaping issues. It worked for seconds or minutes at a time. We saw early signs that it may become broadly useful for coding one day. Fast forward to today. In the last thirty days, I landed 259 PRs -- 497 commits, 40k lines added, 38k lines removed. Every single line was written by Claude Code + Opus 4.5. Claude consistently runs for minutes, hours, and days at a time (using Stop hooks). Software engineering is changing, and we are entering a new period in coding history. And we're still just getting started..

@palashkaria @karpathy 1. Almost always use Plan mode 2. Give Claude a way to verify its output with unit tests, the Claude Chrome extension, or an iOS/Android sim 3. Hold the same bar for human and Claude code. Use /code-review to automate most of code review