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

Show HN: Stop Claude Code from forgetting everything

github.com

Post reply on HN
Print view View original

41–50 of 241 posts

Re: Show HN: Stop Claude Code from forgetting everything

#41

Post by AndyNemmity »

lukev wrote: post #27
JoshGlazebrook wrote: post #18

Is anyone else just completely overwhelmed with the number of things you _need_ for claude code? Agents, sub agents, skills, claud.md, agents.md, rules, hooks, etc. We use Cursor where I work and I find it a good medium for still being in control and knowing what is happening with all of the changes being reviewed in an IDE. Claude feels more like a black box, and one with so many options that it's just overwhelming,…

A claude.md file will give you 90% of what you need. Consider more when you're 50+ hours in and understand what more you want.

In my experience, I'm at the most where I entirely ignore Claude.md - so it's very interesting how many people have very different experiences.

Re: Show HN: Stop Claude Code from forgetting everything

#42

Post by austinbaggio »

senshan wrote: post #7

What is the advantage over summarizing previous sessions for the new one? Or, over continuing the same session and compacting?

You can use it with summaries for sure, but summaries often miss edge cases and long sessions drift. This makes it easier to jump between tasks, come back days later, and reorient without missing something that the summarization or compaction might have gotten rid of. I've often found post-compaction, the memory of even the current session feels so much dumber.

Re: Show HN: Stop Claude Code from forgetting everything

#43

Post by majormajor »

AndyNemmity wrote: post #36
JoshGlazebrook wrote: post #18

Is anyone else just completely overwhelmed with the number of things you _need_ for claude code? Agents, sub agents, skills, claud.md, agents.md, rules, hooks, etc. We use Cursor where I work and I find it a good medium for still being in control and knowing what is happening with all of the changes being reviewed in an IDE. Claude feels more like a black box, and one with so many options that it's just overwhelming,…

I'm the opposite, I find it straight forward to use all these things, and am surprised people aren't getting it. I've been trying to write blogs explaining it recently, but I don't think I'm very good at making it sound interesting to people. What can I explain that you would be interested in? Here was my latest attempt today. https://vexjoy.com/posts/everything-that-can-be-deterministi...

You say "My Claude Code Setup" but where is the actual setup there? I generally agree with everything about how LLMs should be called you say, but I don't see any concrete steps of changing Claude Code's settings in there? Where are the "35 agents. 68 skills. 234MB of context."? Is the implementation of the "Layer 4" programs intended to be left to the reader? That's hardly approachable.

Re: Show HN: Stop Claude Code from forgetting everything

#44

Post by ramoz »

I struggle with these abstractions over context windows, esp when anthropic is actively focused on improving things like compaction, and knowing the eventual* goal is for the models to yave real memory layers baked in. Until then we have to optimize with how agents work best and ephemeral context is a part of that (they weren’t RL’d/trained with memory abstractions so we shouldn’t use them at inference either). Constant rediscovery that is task specific has worked well for me, doesn’t suffer from context decay, though it does eat more tokens.

Otherwise the ability to search back through history is a valuable simple git log/diff or (rip)grep/jq combo over the session directory. Simple example of mine: https://github.com/backnotprop/rg_history

Re: Show HN: Stop Claude Code from forgetting everything

#45

Post by _the_inflator »

JoshGlazebrook wrote: post #18

Is anyone else just completely overwhelmed with the number of things you _need_ for claude code? Agents, sub agents, skills, claud.md, agents.md, rules, hooks, etc. We use Cursor where I work and I find it a good medium for still being in control and knowing what is happening with all of the changes being reviewed in an IDE. Claude feels more like a black box, and one with so many options that it's just overwhelming,…

I like the finetuning aspect to it quite a lot. It makes sense to me. What I achieved now is a very streamlined process of autonomous work of an agent, which can more and more often be simply managed than controlled on a code review level basis for everything.

I agree that this level of finetuning feels overwhelming and might let yourself doubting whether you do utilize Claude to its optimum and the beauty is, that finetunging and macro usage don't interfere, when you stay in your lane.

For example I now don't use the planing agent anymore instead incorporated this process into the normal agents much to the project's advantage. Consistency is key. Anthropic did the right thing.

Codex is quite a different beast and comes from the opposite direction so to say.

I use both, Codex and Claude Opus especially, in my daily work and found them complementary not mutual exclusive. It is like two different evangelists who are on par exercising with different tools to achieve a goal, that both share.

Re: Show HN: Stop Claude Code from forgetting everything

#46

Post by AndyNemmity »

majormajor wrote: post #43
AndyNemmity wrote: post #36

Earlier quoted context omitted.

I'm the opposite, I find it straight forward to use all these things, and am surprised people aren't getting it. I've been trying to write blogs explaining it recently, but I don't think I'm very good at making it sound interesting to people. What can I explain that you would be interested in? Here was my latest attempt today. https://vexjoy.com/posts/everything-that-can-be-deterministi...

You say "My Claude Code Setup" but where is the actual setup there? I generally agree with everything about how LLMs should be called you say, but I don't see any concrete steps of changing Claude Code's settings in there? Where are the "35 agents. 68 skills. 234MB of context."? Is the implementation of the "Layer 4" programs intended to be left to the reader? That's hardly approachable.

I got similar feedback with my first blog post on my do router - https://vexjoy.com/posts/the-do-router/

Here is what I don't get. it's trivial to do this. Mine is of course customized to me and what I do.

The idea is to communicate the ideas, so you can use them in your own setup.

It's trivial to put for example, my do router blog post in claude code and generate one customized for you.

So what does it matter to see my exact version?

These are the type of things I don't get. If I give you my details, it's less approachable for sure.

The most approachable thing I could do would be to release individual skills.

Like I have skills for generating images with google nano banana. That would be approachable and easy.

But it doesn't communicate the why. I'm trying to communicate the why.

Re: Show HN: Stop Claude Code from forgetting everything

#47

Post by ramoz »

dr_dshiv wrote: post #32

I just ask Claude to look at past conversations where I was working on x… it sometimes thinks it can’t see them, but it can. I’ll give this a go though and let you know!

Here is a simple skill (markdown instruction only) that instructs a nice ripgrep approach - with utility of discovering current session.

https://github.com/backnotprop/rg_history

Re: Show HN: Stop Claude Code from forgetting everything

#48

Post by austinbaggio »

bilbo-b-baggins wrote: post #37

Your site advertises careers in San Francisco/Remote. California law requires compensation disclosures.

Good flag, we're still pretty early, I think the strict requirement for compensation disclosures is post 15 employees in CA? Did I get this wrong?

Re: Show HN: Stop Claude Code from forgetting everything

#49

Post by AndyNemmity »

ramoz wrote: post #44

I struggle with these abstractions over context windows, esp when anthropic is actively focused on improving things like compaction, and knowing the eventual* goal is for the models to yave real memory layers baked in. Until then we have to optimize with how agents work best and ephemeral context is a part of that (they weren’t RL’d/trained with memory abstractions so we shouldn’t use them at inference either). Const…

There is certainly a level where at any time you could be building some abstraction that is no longer required in a month, or 3.

I feel that way too. I have a lot of these things.

But the reality is, it doesn't really happen that often in my actual experience. Everyone is very slow as a whole to understand what these things mean, so far you get quite a bit of time just with an improved, customized system of your own.

Post reply on HN