Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Dynamic Workflows in Claude Code

claude.com

Post reply on HN
Print view View original

101–110 of 160 posts

Re: Dynamic Workflows in Claude Code

#101

Post by ithkuil »

Deukhoofd wrote: post #5

I'm going to be honest, this very much reads like an exciting new way to burn up as many tokens as possible. Large amounts of parallel agents that all have all their work double-checked by multiple other agents, and that keeps running for a longer period of time? I feel like there are more efficient ways to tackle the issues given.

Possibly. But otoh one cannot complain that agents don't produce high quality code while at the same time not allowing them to thoroughly go through all the steps required to produce high quality code

Re: Dynamic Workflows in Claude Code

#102

Post by _boffin_ »

bcherny wrote: post #10

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.

This isn't related to Dynamic Workflows, but more on the telemetry / observability side of things.

Why'd you guys not want to allow the traceparent in hooks, but allowed the session.id? Any plans on changing that?

Re: Dynamic Workflows in Claude Code

#103

Post by KronisLV »

wrs wrote: post #28
SkyPuncher wrote: post #12

I don't really get this. At this point, my limiting factor is not how quickly Claude can self-trudge through code. It's whether Claude is going to do the task correctly or not. I need more mechanisms for controlling long-running sessions and dynamically injecting my thoughts, correction, and nudges rather than faster ways to burn through my tokens without knowing if the results are going to be correct.

I think the theoretical answer here is this: "Agents address the problem from independent angles, other agents try to refute what they found, and the run keeps iterating until the answers converge." So you will be supplying the "ground truth" (test suite, detailed spec, whatever) and empower an agent to use it to guide the other agents. Currently a lot of people do this sequentially in the form of multiple code-revie…

> Currently a lot of people do this sequentially in the form of multiple code-review passes by fresh agent sessions looking at the work of previous sessions.

Up until now I've used a review loop approach, where within a Claude Code session I just tell it to spawn three review sub-agents, each with context of what's going on and instructions to look over all of the changed code in search for serious/critical issues, but otherwise a more fresh look at things. It works really well for the most part (token usage aside): https://news.ycombinator.com/item?id=48277011

Re: Dynamic Workflows in Claude Code

#104

Post by Garlef »

wrs wrote: post #28
SkyPuncher wrote: post #12

I don't really get this. At this point, my limiting factor is not how quickly Claude can self-trudge through code. It's whether Claude is going to do the task correctly or not. I need more mechanisms for controlling long-running sessions and dynamically injecting my thoughts, correction, and nudges rather than faster ways to burn through my tokens without knowing if the results are going to be correct.

I think the theoretical answer here is this: "Agents address the problem from independent angles, other agents try to refute what they found, and the run keeps iterating until the answers converge." So you will be supplying the "ground truth" (test suite, detailed spec, whatever) and empower an agent to use it to guide the other agents. Currently a lot of people do this sequentially in the form of multiple code-revie…

Doesn't help if the wrong design is implemented correctly.

Re: Dynamic Workflows in Claude Code

#105

Post by wrs »

tsunamifury wrote: post #46
adamtaylor_13 wrote: post #40

Earlier quoted context omitted.

While pedantically correct, I think the comment above assumed that you've correctly specified the work. If you can't correctly specify your work, AI agents are just going to help you get a non-solution faster.

Isn't coding the act of specificying the work to a processor? And AI agents are supposed to bridge the gap with intelligence from less specificed to more specified or possibly even more intelligent and alternate implementations?

What I meant by "ground truth" is that it is not fuzzy, not AI-evaluated, and not a consensus. The test suite passes or it doesn't. The codebase lints or it doesn't. The performance improved or it didn't.

An agent can help you create the specification, but it's up to you to know whether it's correctly testing that you got the result you wanted.

Re: Dynamic Workflows in Claude Code

#106

Post by hedgehog »

bcherny wrote: post #10

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.

How granular is the control over the internal process?

In my experiments I've had some success modeling the work to be done as a DAG of typed artifacts with a combination of code + LLM doing decomposition, transforms, synthesis, and fitness checking to generate the output. It took me a lot of tries to arrive at that formula and it would be cool to have something more general. I also run part of it against local compute because it would be far beyond my budget to do it all on Opus, so something for that would be nice too.

Re: Dynamic Workflows in Claude Code

#107

Post by verve_rat »

bcherny wrote: post #19
thallavajhula wrote: post #13

Earlier quoted context omitted.

Hi Boris! Thanks for Claude Code. Is there an example of how y'all use Dynamic Workflows internally that you could share with the rest of us here so that we can mimic something similar?

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…

None of those are helpful examples we could mimic to figure out how to use the tools.

This reads like a CV, not trying to help or educate.

Re: Dynamic Workflows in Claude Code

#109

Post by kian »

trjordan wrote: post #9

It feels like we're far past the point of where having AI do more faster is helpful. It's telling that they used "rewrite Bun in Rust" as the proof point here. It's cool! But the vast majority of software engineering doesn't start with tens of thousands of tests, where making them pass is the whole job. In my experience, AI still drifts from what I meant it to do on anything bigger than building a widget. My time is…

"In my experience, AI still drifts from what I meant it to do on anything bigger than building a widget."

I've had code bases with tens of thousands of lines of code built from scratch that I hand-reviewed every line of and worked with the AI to improve, and haven't had this issue. I feel like a significant part of this is due to an involved /plan stage -- going back and forth on building out a plan for what you want the AI to do involves surfacing the assumptions that you would have called drift if you asked them to implement it directly from your prompt.

Once the plan has been refined and is what I want it to be, getting it to implement everything in TDD style has for the most part given me 100% working code, as I wanted it to be, without issues. It definitely helps that I'm a principal-level engineer with extensive architectural experience -- but if you're able to tell the AI in detail what you want, have it ask questions for clarifications, and read through a plan before getting it implemented, and have a solid testing plus manual qa process (automated by chrome devtools mcp) in place, I've find that you can one-shot complex features, rewrites, and even not-insignificant applications that would have taken days to write by hand in a few hours.

Re: Dynamic Workflows in Claude Code

#110

Post by gfunk911 »

bcherny wrote: post #10

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.

How much overlap do you feel like dynamic workflows have with RLMs?
Post reply on HN