9 comments

  • CuriouslyC 3 hours ago
    As someone who's built a project in this space, this is incredibly unreliable. Subagents don't get a full system prompt (including stuff like CLAUDE.md directions) so they are flying very blind in your projects, and as such will tend to get derailed by their lack of knowledge of a project and veer into mock solutions and "let me just make a simpler solution that demonstrates X."

    I advise people to only use subagents for stuff that is very compartmentalized because they're hard to monitor and prone to failure with complex codebases where agents live and die by project knowledge curated in files like CLAUDE.md. If your main Claude instance doesn't give a good handoff to a subagent, or a subagent doesn't give a good handback to the main Claude, shit will go sideways fast.

    Also, don't lean on agents for refactoring. Their ability to refactor a codebase goes in the toilet pretty quickly.

    • zarzavat 2 hours ago
      > Their ability to refactor a codebase goes in the toilet pretty quickly.

      Very much this. I tried to get Claude to move some code from one file to another. Some of the code went missing. Some of it was modified along the way.

      Humans have strategies for refactoring, e.g. "I'm going to start from the top of the file and Cut code that needs to be moved and Paste it in the new location". LLM don't have a clipboard (yet!) so they can't do this.

      Claude can only reliably do this refactoring if it can keep the start and end files in context. This was a large file, so it got lost. Even then it needs direct supervision.

    • theshrike79 3 hours ago
      I don't use subagents to do things, they're best for analysing things.

      Like "evaluate the test coverage" or "check if the project follows the style guide".

      This way the "main" context only gets the report and doesn't waste space on massive test outputs or reading multiple files.

      • olivermuty 3 hours ago
        This is only a problem if an agent is made in a lazy way (all of them).

        Chat completion sends the full prompt history on every call.

        I am working on my own coding agent and seeing massive improvements by rewriting history using either a smaller model or a freestanding call to the main one.

        It really mitigates context poisoning.

        • ixsploit 6 minutes ago
          I do something similar and I have the best results of not having a history at all, but setting the context new with every invokation.
        • CuriouslyC 2 hours ago
          There's a large body of research on context pruning/rewriting (I know because I'm knee deep in benchmarks in release prep for my context compiler), definitely don't ad hoc this.
        • mattmanser 2 hours ago
          Everyone complains that when you compact the context, Claude tends to get stupid

          Which as far as I understand it is summarizing the context with a smaller model.

          Am I misunderstanding you, as the practical experience of most people seem to contradict your results.

          • NitpickLawyer 1 hour ago
            One key insight I have from having worked on this from the early stages of LLMs (before chatgpt came out) is that the current crop of LLM clients or "agentic clients" don't log/write/keep track of success over time. It's more of a "shoot and forget" environment right now, and that's why a lot of people are getting vastly different results. Hell, even week to week on the same tasks you get different results (see the recent claude getting dumber drama).

            Once we start to see that kind of self feedback going in next iterations (w/ possible training runs between sessions, "dreaming" stage from og RL, distilling a session, grabbing key insights, storing them, surfacing them at next inference, etc) then we'll see true progress in this space.

            The problem is that a lot of people work on these things in silos. The industry is much more geared towards quick returns now, having to show something now, rather than building strong fo0undations based on real data. Kind of an analogy to early linux dev. We need our own Linus, it would seem :)

            • ako 43 minutes ago
              I’ve experimented with feature chats, so start a new chat for every change, just like a feature branch. At the end of a chat I’ll have it summarize the the feature chat and save it as a markdown document in the project, so the knowledge is still available for next chats. Seems to work well.

              You can also ask the llm at the end of a feature chat to prepare a prompt to start the next feature chat so it can determine what knowledge is important to communicate to the next feature chat.

              Summarizing a chat also helps getting rid of wrong info, as you’ll often trial and error towards the right solution. You don’t want these incorrect approaches to leak into the context of the next feature chat, maybe just add the “don’t dos” into a guidelines and rules document so it will avoid it in the future.

            • troupo 1 hour ago
              > don't log/write/keep track of success over time.

              How do you define success of a model's run?

              • NitpickLawyer 37 minutes ago
                Lots of ways. You could do binary thumbs up/down. You could do a feedback session. You could look at signals like "acceptance rate" (for a pr?) or "how many feedback messages did the user send in this session", and so on.

                My point was more on tracking these signals over time. And using them to improve the client, not just the model (most model providers probably track this already).

  • sixhobbits 36 minutes ago
    I often see people making these sub agents modelled on roles like product manager, back end developer, etc.

    I spent a few hours trying stuff like this and the results were pretty bad compared to just using CC with no agent specific instructions.

    Maybe I needed to push through and find a combination that works but I don't find this article convincing as the author basically says "it works" without showing examples or comparing doing the same project with and without subagents.

    Anyone got anything more convincing to suggest it's worth me putting more time into building out flows like this instead of just using a generic agent for everything?

    • redrove 1 minute ago
      This has been my experience so far as well. It seems like just basic prompting gets me much further than all these complicated extras.

      At some point you gotta stop and wonder if you’re doing way too much work managing claude rather than your business problem.

  • dutchCourage 2 hours ago
    That sounds crazy to me, Claude Code has so many limitations.

    Last week I asked Claude Code to set up a Next.js project with internationalization. It tried to install a third party library instead of using the internationalization method recommended for the latest version of Next.js (using Next's middleware) and could not produce of functional version of the boilerplate site.

    There are some specific cases where agentic AI does help me but I can't picture an agent running unchecked effectively in its current state.

  • simianwords 2 hours ago
    Slightly off topic but I would really like agentic workflow that is embedded in my IDE as well as my code host provider like GitHub for pull requests.

    Ideally I would like to spin off multiple agents to solve multiple bugs or features. The agents have to use the ci in GitHub to get feedback on tests. And I would like to view it on IDE because I like the ability to understand code by jumping through definitions.

    Support for multiple branches at once - I should be able to spin off multiple agents that work on multiple branches simultaneously.

    • Jare 1 hour ago
      Would that be solved by having several clones of your repo, each with a IDE and a Claude working on each problem? Much like how multiple people work in parallel.
      • simianwords 1 hour ago
        Yeah but it’s not ideal. I thought of this too.
  • raminf 3 hours ago
    Was going to ask how much all this cost, but this sort of answers it:

    > "Managing Cost and Usage Limits: Chaining agents, especially in a loop, will increase your token usage significantly. This means you’ll hit the usage caps on plans like Claude Pro/Max much faster. You need to be cognizant of this and decide if the trade-off—dramatically increased output and velocity at the cost of higher usage—is worth it."

  • Frannky 3 hours ago
    Is it a good idea to generate more code faster to solve problems? Can I solve problems without generating code?

    If code is a liability and the best part is no part, what about leveraging Markdown files only?

    The last programs I created were just CLI agents with Markdown files and MCP servers(some code here but very little).

    The feedback loop is much faster, allowing me to understand what I want after experiencing it, and self-correction is super fast. Plus, you don't get lost in the implementation noise.

    • ehnto 3 hours ago
      Code you didn't write is an even bigger liability, because if the AI gets off track and you can't guide it back, you may have to spend the time to learn it's code and fix the bugs.

      It's no different to inheriting a legacy application though. As well, from the perspective of a product owner, it's not a new risk.

      • zarzavat 2 hours ago
        Claude is a junior. The more you work with it, the more you get a feel for which tasks it will ace unsupervised (some subset of grunt work) and which tasks to not even bother using it for.

        I don't trust Claude to write reams of code that I can't maintain except when that code is embarrassingly testable, i.e it has an external source of truth.

      • Frannky 2 hours ago
        There is no generated code. It is just a user interacting with a CLI terminal(via librechat frontend), guided by Markdown files, with access to MCPs
    • Joel_Mckay 2 hours ago
      Using LLMs to code poses a liability most people can't appreciate, and won't admit:

      https://www.youtube.com/watch?v=wL22URoMZjo

      Have a great day =3

  • jackblemming 1 hour ago
    All of this stuff seems completely insane to me and something my coding agent should handle for me. And it probably will in a year.
  • zachwills 3 days ago
    Follow up from my last post; lots were asking for more examples. I will be around if anybody has questions this morning.
    • bazhand 3 days ago
      Can it work without Linear, using md files?
  • user3939382 2 hours ago
    I’ve got this down to a science.