Live data from Hacker News

Dynamic Workflows in Claude Code

claude.com

71–80 of 160 posts

Re: Dynamic Workflows in Claude Code

#71
post #28

Earlier quoted context omitted.

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…

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…

This matches my experience.

I've had to put a fair chunk of effort in to skills that will run deterministic mechanisms to unslop a codebase (cyclomatic complexity grading has been really helpful here) as invariably some amount of guidance around principles will be missed over time. I've found it does help, though. Certainly I'm getting overall better results from Flash and Sonnet over multiple runs for fairly modest token increases. GPT 5.5 less so, but that's because it scores better in a first pass. I won't really know until I gauge it at the end of my sub month which has been more cost efficient for me all things considered.

Re: Dynamic Workflows in Claude Code

#72

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 have heard of "token-maxxing" but I have not heard of "correctness-maxxing" or "quality-maxxing".

Not with those exact terms, but it is certainly being discussed. Wes McKinney said in a recent talk that with current coding agents there’s no longer an excuse for shipping suboptimal code that takes on tech debt. Writing tests has never been cheaper, writing custom fuzzers, linters, and other harnesses that serve as guardrails has never been cheaper. His take is that “we didn’t have enough engineering time to do it right” is no longer an excuse, and the only excuses left are that you don’t know any better or you have bad taste.

Re: Dynamic Workflows in Claude Code

#73

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?

Yep. And yet, there's still some level of specification you have to do.

Re: Dynamic Workflows in Claude Code

#74
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.

I have my own version and the workflow keyword conflicts with it rather heavily. Will there be a way to disable that prompt section/keyword?

Re: Dynamic Workflows in Claude Code

#75
post #28

Earlier quoted context omitted.

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…

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…

The problem is that we have an ever growing and large number of constraints, and not following even a single one means the result is sloppy.

I don’t see them fixing this any time soon, and thus human in the loop is a requirement to use these tools effectively. That is unless you love your slot machine dopamine rush enough to ignore quality gates and respect for your peers time.

Re: Dynamic Workflows in Claude Code

#76

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.

This is my experience. Quantity of output is not the issue right now. Quality is. But I’m not sure if this will ever be solved for, given LLMs are non-deterministic sophisticated autocomplete at their core.

Sure, ‘human in the loop’ and all that jazz, but I feel like my knowledge suffers even with this approach. I have to use llms w pinpoint focus to get decent results.

The original copilot completions behavior might be peak llm performance for coding, sans having an agent write boilerplate and such.

Re: Dynamic Workflows in Claude Code

#77
I’m gonna try this one on tsz. So far Codex /goal has been great

https://tsz.dev

So far Codex /goal has been amazing but Claude Code /goal or even /loop does not work hard enough and gives up. I have observed it just claiming it’s “iterating” in a broken loop or simply giving up.

Re: Dynamic Workflows in Claude Code

#80

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.

The answer for me has been actually more tokens, and create even more layers of automated verification
Post reply on HN