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

221–230 of 241 posts

Re: Show HN: Stop Claude Code from forgetting everything

#221

Post by everfrustrated »

Normal_gaussian wrote: post #96
brigandish wrote: post #58

Earlier quoted context omitted.

How can you - or any human - review that much code?

When I'm coding I have about 6 instances of VSCode on the go at once; each with their own worktree and the terminal is a dangerous cc in docker. most of the time they are sitting waiting for me. Generally a few are doing spec work/reporting for me to understand something - sometimes with issue context; these are used to plan or redirect my attention if I might've missed something. A few will be just hacking on issues…

>I've TL'd and PM'd as well as IC'd. Now my IC work feels a lot more like a cross between being a TL

Interesting... I've been in management for a few years now and recently doing some AI coding work. I've found my skills as a manager/TL are far more adaptable to getting the best out of AI agents than my skills as a coder.

Re: Show HN: Stop Claude Code from forgetting everything

#222

Post by rahimnathwani »

qudat wrote: post #14

Have you tried https://github.com/steveyegge/beads

Beads is awesome. I've been using it with a greenfield React Native hobby project. I did some work up front on the spec (with help from AI), and started the repo from a boilerplate, but after that every single bead (epic, ticket) and every single line of code has been written by AI (using a mix of claude, codex, cursor-agent/composer-1).

The app works. When I feel like working on it, I just open a CLI coding agent and say 'start working'. Then every so often I say 'commit and push' or 'find opportunities to improve the code base by refactoring, and create an issue for each opportunity'.

(I followed the instructions to add the boilerplate instructions for both bd and bv, to AGENTS.md)

Re: Show HN: Stop Claude Code from forgetting everything

#223

Post by troupo »

AndyNemmity wrote: post #215
troupo wrote: post #172

Earlier quoted context omitted.

> You can generally tell which ones are actually doing something if they are using skills, with programs in them. > Otherwise, you're just feeding in different prompts and steps "skills" are literally just .md files with different prompts and steps. > That's actually adding something claude code doesn't have, instead of just saying "You are an expert in blah" It's not adding anything but a prompt saying "when asked t…

Skill are md files, but they are not just that. They are also scripts. That's what adding things are. You can make a skill that is just a prompt, but that misses the point of the value. You're packaging the tool with the skill, or multiple tools to do a single thing.

In the end it's still an .md file pointing to a script that ends being just a prompt for the agent that the agent may or may not pick up, may or may not discover, may or may not forget after context compaction etc.

There's no inherent magic to skills, or any fundamental difference between them and "just feeding in different prompts and steps". It literally is just feeding different prompt and steps.

Re: Show HN: Stop Claude Code from forgetting everything

#224

Post by austinbaggio »

ramoz wrote: post #213
christinetyip wrote: post #201

Earlier quoted context omitted.

I mostly agree with this, if the goal were “better persistent memory inside Claude Code,” that wouldn’t be very interesting. For a single agent and a single tool, keeping project specs and decisions in markdown and explicitly pointing the model at them works well. We do that too. What we’re focused on is a different boundary: memory that isn’t owned by a specific agent or tool. Once you start switching between tools…

If markdown in a git repository isn’t good enough for collaboration, then why would any plugged in abstraction be better? You imply you have a solution for current wholistic state. For this you would need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost). That narrative becomes harsher once you pivot to “general pu…

| need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost).

I agree. We are looking at some metr benchmarks, not expecting a simple answer to this, but do you have any in mind you find compelling?

Re: Show HN: Stop Claude Code from forgetting everything

#225

Post by austinbaggio »

everfrustrated wrote: post #221
Normal_gaussian wrote: post #96

Earlier quoted context omitted.

When I'm coding I have about 6 instances of VSCode on the go at once; each with their own worktree and the terminal is a dangerous cc in docker. most of the time they are sitting waiting for me. Generally a few are doing spec work/reporting for me to understand something - sometimes with issue context; these are used to plan or redirect my attention if I might've missed something. A few will be just hacking on issues…

>I've TL'd and PM'd as well as IC'd. Now my IC work feels a lot more like a cross between being a TL Interesting... I've been in management for a few years now and recently doing some AI coding work. I've found my skills as a manager/TL are far more adaptable to getting the best out of AI agents than my skills as a coder.

Same, I was a very average dev coming out of CS, and a PM before this. I find that my product training has been more useful, especially with prototypes, but I do leave nearly all of the hard system, infra, and backend work to my much much more competent engineering teammates.

Re: Show HN: Stop Claude Code from forgetting everything

#226

Post by lloydatkinson »

llmslave2 wrote: post #72
lloydatkinson wrote: post #69

> Not magic. Not AGI. Just state. Why did you need to use AI to write this post?

Their brains are mush, lost the ability to focus on a task or do any deep thinking. Just proooooooooompt.

insert prooomptorrrrr soyjack meme

Re: Show HN: Stop Claude Code from forgetting everything

#228

Post by ramoz »

austinbaggio wrote: post #224
ramoz wrote: post #213

Earlier quoted context omitted.

If markdown in a git repository isn’t good enough for collaboration, then why would any plugged in abstraction be better? You imply you have a solution for current wholistic state. For this you would need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost). That narrative becomes harsher once you pivot to “general pu…

| need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost). I agree. We are looking at some metr benchmarks, not expecting a simple answer to this, but do you have any in mind you find compelling?

Not really. But, You can go viral again with a "Coding Agents with memory build better software using less tokens" showcasing how you benchmarked a "twitter rebuild" -

1. Setup Claude Code to build some layers of the stack

2. Setup Codex to build others.

In one instance equip them both with your product. Maybe bake in some tribal knowledge.

In another instance let them work raw.

In both instances, capture:

     - Time to completion
     - Tokens spent
     - Ability to meet original spec
     - Subjective quality 
     - Number of errors and categorize between the layers, to state something like "raw-claude's backend kept failing with raw-codex's frontend" etc
I imagine this benchmark working well in your favor.

Re: Show HN: Stop Claude Code from forgetting everything

#229

Post by johann8384 »

I have markdown files in ~/.claude/guides that I refer to, my subagents have instructions about, and my claude.md in several projects reference them when relevant.

This seems like it wouldn't accomplish much more than those methods. It knows my stack preferences, what I want commit messages to look like, etc.

Re: Show HN: Stop Claude Code from forgetting everything

#230

Post by dnautics »

AndyNemmity wrote: post #216
dnautics wrote: post #188

Earlier quoted context omitted.

no that makes no sense. the skill doesn't do anything by itself, the mcp (can be) attached to a deterministic oracle that can return correct information.

But the skill includes the scripts to do things. So in my nano banana image generation skill, it contains a python script that does all the actual work. The skill just knows how to call the python script. We're attaching tools to the md files. This is at the granular level of how to hammer a nail, how to use a screw driver, etc. And then the agent, the handyman, has his tool box of skills to call depending on what he…

lets say i'm in erlang. you gonna include a script to unpack erlang bytecode across all active modules and look through them for a function call? oorrr... have that code running on localhost:4000 so that its a single invocation away, versus having the llm copypasta the entire script you provided and pray for the best?
Post reply on HN