Hacker News: bcherny

New comment by bcherny in "Anthropic, please ship an official Claude Desktop for Linux"

bcherny — Sun, 07 Jun 2026 18:55:12 +0000

Boris from the team here — we’re looking into it.

New comment by bcherny in "AI Agent Guidelines for CS336 at Stanford"

bcherny — Mon, 01 Jun 2026 19:29:25 +0000

For those using Claude Code, I recommend Learning mode to instruct Claude to walk you through implementing the solution yourself rather than doing it for you. It’s very helpful when diving into a new domain, and helps build lower level intuition.

To enable it, run /config > output styles > Learning

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 18:56:51 +0000

Yep! Set disableWorkflows:true in your settings.json

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:53:19 +0000

Looking

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:47:51 +0000

Typo! Edited

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:47:25 +0000

Yes!

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:47:20 +0000

Yes, it also helps! That's a place where raw model capability is the most helpful, but we do find that some dynamic workflow configurations can be helpful too.

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:36:47 +0000

There's two main differences:

1. Support for 1-2 OOMs more agents, to do more work in parallel

2. A phased, semi-structured approach where work happens in steps

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:32:41 +0000

JavaScript, running locally or in the cloud.

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:32:15 +0000

Yes, more docs + technical details coming soon.

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:31:20 +0000

We generally build features into the Claude Agent SDK, which is shared by CLI, Desktop, VSCode, and cloud.

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:30:18 +0000

Hey, yep. A few things I personally used dynamic workflows for over the last few weeks:

1. Autonomously landed 20+ optimizations to reduce Claude Code's token usage by ~15%

2. Ported tree-sitter, color-diff, yoga-layout, and a number of other WASM and Rust native modules to TypeScript, improving CPU and memory use by 2-10x in the process

3. Made our CI faster, and repeatedly found and fixed flaky tests (with /loop)

4. Migrated from regex-based bash static analysis to tree-sitter, reducing false positive permission prompts by 45%

5. Reduced Claude Agent SDK startup time by 61%, by repeatedly profiling and optimizing the startup path, putting up a number of PRs in the process

6. Shipped 69 code simplification PRs, deleting >10k lines of code

New comment by bcherny in "Dynamic Workflows in Claude Code"

bcherny — Thu, 28 May 2026 17:24:14 +0000

A few of us from the Claude Code team will be hanging around if anyone has questions! Very excited for this launch -- dynamic workflows have been a game changer for engineering here at Anthropic. Can't wait to hear what you think.

New comment by bcherny in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

bcherny — Wed, 27 May 2026 16:57:35 +0000

Totally. You can do that now, and Claude will know to use /code-review.

New comment by bcherny in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

bcherny — Wed, 27 May 2026 16:57:02 +0000

Yep, you can add free-form input. Will update /simplify to only check for code quality and not bugs (the way it used to work), that's a good suggestion.

New comment by bcherny in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

bcherny — Wed, 27 May 2026 16:31:14 +0000

/code-review has a specific prompt that we've found is a good balance of precision, recall, and cost. You could totally roll your own prompt also.

New comment by bcherny in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

bcherny — Wed, 27 May 2026 16:10:18 +0000

Hey, Boris from the CC team here. I agree, we're working on consolidating these. Going forward it will just be the built-in /code-review skill.

Here's how to use the skill on the latest version:

/code-review # do a balanced code review. checks for bugs and inconsistencies, poor code quality, duplication, band aids, etc.

/code-review --fix # same as above, but also fix the issues

# choose an explicit effort level (defaults to your current effort level). all of these also accept --fix:

/code-review low

/code-review medium

/code-review high

/code-review xhigh

/code-review max

# do an expensive and extremely thorough review (reliably catches >99% of bugs, costs $3-20 per review depending on complexity):

/code-review ultra

Open to feedback if anyone has feedback or ideas for how to make these even nicer to use.

New comment by bcherny in "An update on recent Claude Code quality reports"

bcherny — Fri, 24 Apr 2026 05:51:13 +0000

Yes! This is what we’re trying next.

New comment by bcherny in "An update on recent Claude Code quality reports"

bcherny — Fri, 24 Apr 2026 05:49:01 +0000

We anticipated the default would be the best option for most people. We were wrong, so we reverted the default.

New comment by bcherny in "An update on recent Claude Code quality reports"

bcherny — Thu, 23 Apr 2026 23:45:49 +0000

Yep, agree. We added a little "/clear to save XXX tokens" notice in the bottom right, and will keep iterating on this. Thanks for being an early user!