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

141–150 of 160 posts

Re: Dynamic Workflows in Claude Code

#141

Post by unshavedyak »

fredoliveira wrote: post #112
unshavedyak wrote: post #88

Earlier quoted context omitted.

VSCode has an official client? Given IDE usage is being restricted from Claude Code via the CC SDK tokens going to the Claude API rather than your CC Subscription, i'm unclear which IDEs can actually use claude code now. Eg is Zed capable of using a Claude Code Subscription?

> is Zed capable of using a Claude Code Subscription? Yes. Zed connects to Claude Code via ACP.

Oh, yea here's all the proof you need. Even Zed themselves admit you won't be able to use Claude Code via ACP via Subscription: https://zed.dev/blog/terminal-threads

So yea, bcherny didn't reply to me but as far as i can tell - No, Zed nor VSCode will have Claude Code natively in it. The best we can do is embed a Terminal into the editor and run CC in that.

With that said, because bcherny advertised VSCode, i'm going to guess VSCode is going to get special treatment. Really annoying.

Re: Dynamic Workflows in Claude Code

#142

Post by grim_io »

erispoe wrote: post #132
vadansky wrote: post #60

Earlier quoted context omitted.

I don't know, maybe I'm doing it wrong but I feel LLMs add a slop debt, and each agent pass just exuberates it. Like I had an LLM implement a spec and said it was done... Except it had a ton of `casts` everywhere. Okay, my bad, I should have been clear "NO CASTS", so I use the LLM to remove the casts, except it just kept making things more and more complicated and ugly. It took me taking a break and having a shower t…

How would you prevent a junior engineer doing this mistake? Presumably, you would setup a lint rule. Do the same for LLMs. Run the linter after each edit through a hook, give feedback to the LLM. Write your lint rules with clear explanations of why the behavior is a problem, and nudges to the good behavior.

You wouldn't prevent the junior from making this mistake.

You would correct them once or twice, and they won't make the mistake again.

It's something we can't do with LLM's currently, so we all just try(and fail) to predict any possible failure ever, and then somehow try to cram it into the limited context.

Re: Dynamic Workflows in Claude Code

#143

Post by hbarka »

mrud wrote: post #140
hbarka wrote: post #47

Earlier quoted context omitted.

Hi Boris. Love the velocity of features. Are you planning on adding a secrets manager? Enterprise workflows almost always require an encrypted parameter or calling a secret.

I think they have vaults[0] which provide it. I don't think this is available on the non platform side. [0] https://platform.claude.com/docs/en/managed-agents/vaults

This is it, thank you. I’m surprised I couldn’t get Claude to surface this capability.

Re: Dynamic Workflows in Claude Code

#144

Post by thefivetoes »

grim_io wrote: post #142
erispoe wrote: post #132

Earlier quoted context omitted.

How would you prevent a junior engineer doing this mistake? Presumably, you would setup a lint rule. Do the same for LLMs. Run the linter after each edit through a hook, give feedback to the LLM. Write your lint rules with clear explanations of why the behavior is a problem, and nudges to the good behavior.

You wouldn't prevent the junior from making this mistake. You would correct them once or twice, and they won't make the mistake again. It's something we can't do with LLM's currently, so we all just try(and fail) to predict any possible failure ever, and then somehow try to cram it into the limited context.

[flagged]

Re: Dynamic Workflows in Claude Code

#145

Post by Wowfunhappy »

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…

This reminds me of something I do manually all the time (tell Claude to do something, ask another instance what the first one did wrong, etc), and it has given me good results. If the harness can now automate that, it seems great!

Re: Dynamic Workflows in Claude Code

#146

Post by rendaw »

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…

So, theoretically, in order to get claude to perform properly you just have to have a perfect spec up front, that anticipates all issues and contains no ambiguity?

Re: Dynamic Workflows in Claude Code

#149

Post by Syntaf »

Tested this out on a 5x max plan, turns out I spun up 62 Opus 4.8 1M sub-agents for my dynamic workflow and maxed out my ~5hr cap in..... 18 minutes?

Oops, but probably good to know that this is not a cheap feature -- next time I'll have to figure out how to tune the workflows to use Haiku / Sonnet

Post reply on HN