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

The Claude Code Framework Wars

shmck.substack.com

Post reply on HN
Print view View original

51–60 of 71 posts

Re: The Claude Code Framework Wars

#51

Post by grim_io »

bicx wrote: post #49
grim_io wrote: post #46

I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…

I adopted a couple practices (using dev containers and worktrees) just to make life a little easier. I also built my own shell script “framework” to help manage the worktrees and create project files. However, that took me just a couple days to do on my own (also using CC), and it didn’t lock me into a specific tool. I do agree that context poisoning is a real thing to watch out for. Coincidentally, I’d noticed MCP e…

I'm considering removing serena MCP, since cc got better with its own tools.

The new /context cc command is great for visualizing what uses how much of the context.

On the other hand, I'm curious about dagger's container-use MCP. https://container-use.com/agent-integrations

Re: The Claude Code Framework Wars

#53

Post by sharts »

context management seems like low level programming where you need to carefully place the right things on cpu registers to do the operation you want correctly.

On difference is that we have less control of the context to add/remove things per task necessary.

Re: The Claude Code Framework Wars

#54

Post by evolve2k »

Leynos wrote: post #40
fny wrote: post #39

Earlier quoted context omitted.

I'm pretty convinced the only developers who think we're on the cusp of AGI code exclusively in Python or JavaScript.

GPT-5 is a dab hand at Rust

I was hearing that it was good with writing Ruby on Rails as the rails community is so structured already in where things go and sorta the Rails way of writing the code. Anyone have experience with this?

Re: The Claude Code Framework Wars

#55

Post by faangguyindia »

I often wonder why agent is not allowed to manage its own context like humans do?

Why recycle full history into every future turn until you run out of context window?

Perhaps letting agent manage its own context while knowing what an effective context and the harm or going over context or smartly making that tradeoff, it can navigate the tasks better?

Re: The Claude Code Framework Wars

#56

Post by nicwolff »

grim_io wrote: post #46

I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…

This article doesn't mention "subagents" https://docs.anthropic.com/en/docs/claude-code/sub-agents which makes me wonder when it was written. I'm finding that just delegating "scan the memory bank for information relevant to the current task" and "run the unit and functional tests and report back only the failures or coverage" to subagents does a lot to keep the main agent's context from filling up.

Re: The Claude Code Framework Wars

#57

Post by bdangubic »

nicwolff wrote: post #56
grim_io wrote: post #46

I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…

This article doesn't mention "subagents" https://docs.anthropic.com/en/docs/claude-code/sub-agents which makes me wonder when it was written. I'm finding that just delegating "scan the memory bank for information relevant to the current task" and "run the unit and functional tests and report back only the failures or coverage" to subagents does a lot to keep the main agent's context from filling up.

> which makes me wonder when it was written

On Sept 6, 2025

Re: The Claude Code Framework Wars

#59

Post by 3uler »

nicwolff wrote: post #56
grim_io wrote: post #46

I've tried some of those "frameworks" for claude code, but it's difficult to measure any objective improvement. I tend to lean towards them being snake oil. A lot of process and ritual around using them, but for what? I don't think the models themselves are a good fit for the way these frameworks are being used. It probably goes against their training. Now we try to poison the context with lots of (for my actual task…

This article doesn't mention "subagents" https://docs.anthropic.com/en/docs/claude-code/sub-agents which makes me wonder when it was written. I'm finding that just delegating "scan the memory bank for information relevant to the current task" and "run the unit and functional tests and report back only the failures or coverage" to subagents does a lot to keep the main agent's context from filling up.

Many of the frameworks mentioned leverage subagents

Re: The Claude Code Framework Wars

#60

Post by troupo »

signatoremo wrote: post #43
troupo wrote: post #4

> a set of rules, roles, and workflows that make its output predictable and valuable. Let me stop you right there. Are you seriously talking about predictable when talking about a non-deterministic black box over which you have no control?

Huh? I guarantee you, if you give two different developers tbe exact sane set of requirements, that you’d get two very different programs. Try it. They likely perform differently also, performance- or resource-wise. Would you still call that predictable? Of course you would, as long as they meet your requirements. Put it another way, anything is unpredictable depending on your level of scrutiny. AI is likely less pre…

> Of course you would, as long as they meet your requirements.

Key word: "as long as they meet your requirements".

I've yet to meet an LLM that can predictably do that. Even on the same code with the same tools/prompt/rituals a few hours apart.

> AI is likely less predictable than human, doesn’t mean it isn’t helpful.

I'm struggling to see where I said they weren't helpful or that I dismissed them

Post reply on HN