HackerLangs
TopNewTrendsCommentsPastAskShowJobs

bcherny

no profile record

Submissions

We've rewritten Claude Code's terminal rendering to reduce flickering by 85%

github.com
3 points·by bcherny·7 เดือนที่ผ่านมา·3 comments

comments

bcherny
·เดือนที่แล้ว·discuss
Boris from the team here — we’re looking into it.
bcherny
·เดือนที่แล้ว·discuss
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
bcherny
·เดือนที่แล้ว·discuss
Yep! Set disableWorkflows:true in your settings.json
bcherny
·เดือนที่แล้ว·discuss
Looking
bcherny
·เดือนที่แล้ว·discuss
Typo! Edited
bcherny
·เดือนที่แล้ว·discuss
Yes!
bcherny
·เดือนที่แล้ว·discuss
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.
bcherny
·เดือนที่แล้ว·discuss
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
bcherny
·เดือนที่แล้ว·discuss
JavaScript, running locally or in the cloud.
bcherny
·เดือนที่แล้ว·discuss
Yes, more docs + technical details coming soon.
bcherny
·เดือนที่แล้ว·discuss
We generally build features into the Claude Agent SDK, which is shared by CLI, Desktop, VSCode, and cloud.
bcherny
·เดือนที่แล้ว·discuss
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
bcherny
·เดือนที่แล้ว·discuss
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.
bcherny
·เดือนที่แล้ว·discuss
Totally. You can do that now, and Claude will know to use /code-review.
bcherny
·เดือนที่แล้ว·discuss
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.
bcherny
·เดือนที่แล้ว·discuss
/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.
bcherny
·เดือนที่แล้ว·discuss
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.
bcherny
·3 เดือนที่ผ่านมา·discuss
Yes! This is what we’re trying next.
bcherny
·3 เดือนที่ผ่านมา·discuss
We anticipated the default would be the best option for most people. We were wrong, so we reverted the default.
bcherny
·3 เดือนที่ผ่านมา·discuss
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!