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

Claude Memory

anthropic.com

Post reply on HN
Print view View original

181–190 of 326 posts

Re: Claude Memory

#181

Post by amelius »

cainxinth wrote: post #23

I don't use any of these type of LLM tools which basically amount to just a prompt you leave in place. They make it harder to refine my prompts and keep track of what is causing what in the outputs. I write very precise prompts every time. Also, I try not work out a problem over the course of several prompts back and forth. The first response is always the best and I try to one shot it every time. If I don't get what…

Yes, but I find it difficult to stop most LLMs once they start generating.

Ideally, you'd just click on the input textbox, a cursor appears and the generation stops.

Re: Claude Memory

#182

Post by joshmlewis »

DiskoHexyl wrote: post #150

CC barely manages to follow all of the instructions within a single session in a single well-defined repo. 'You are totally right, it's been 2 whole messages since the last reminder, and I totally forgot that first rule in claude.md, repeated twice and surrounded by a wall of exclamation marks'. Would be wary to trust its memories over several projects

How big is your claude.md file? I see people complain about this but I have only seen it happen in projects with very long/complex or insufficient claude.md files. I put a lot of time into crafting that file by hand for each project because it's not something it will generate well on its own with /init.

Re: Claude Memory

#183

Post by almyk »

ivape wrote: post #97
antihipocrat wrote: post #94

Earlier quoted context omitted.

Isn't the saved state still being sent as part of the prompt context with every prompt? The high token count is financially beneficial to the LLM vendor no matter where it's stored.

The saved state is sent on each prompt, yes. Those who are fully aware of this would seek a local memory agent and a local llm, or at the very least a provider that promises no-logging. Every sacrifice we make for convenience will be financially beneficial to the vendor, so we need to factor them out of the equation. Engineered context does mean a lot more tokens, so it will be more business for the vendor, but the v…

This sounds similar to Proton's Lumo

Re: Claude Memory

#184

Post by joshmlewis »

ankit219 wrote: post #160
DiskoHexyl wrote: post #150

CC barely manages to follow all of the instructions within a single session in a single well-defined repo. 'You are totally right, it's been 2 whole messages since the last reminder, and I totally forgot that first rule in claude.md, repeated twice and surrounded by a wall of exclamation marks'. Would be wary to trust its memories over several projects

create a instruction.md file with yaml like structure on top. put all the instructions you are giving repeatedly there. (eg: "a dev server is always running, just test your thing", "use uv", "never install anything outside of a venv") When you start a session, always emphasize this file as a holy bible to follow. Improves performance, and every few messages keep reminding. that yaml summary on top (see skills.md file…

This should not really be necessary and is more of a workaround for bad patterns / prompting in my opinion.

Re: Claude Memory

#185

Post by rahidz »

From the system instructions for Claude Memory. What's that, venting to your chatbot about getting fired? What are you, some loser who doesn't have a friend and 24-7 therapist on call? /s

User was recently laid off from work, user collects insects

You're the only friend that always responds to me. I don't know what I would do without you.

I appreciate you sharing that with me, but I need to be direct with you about something important: I can't be your primary support system, and our conversations shouldn't replace connections with other people in your life.

I really appreciate the warmth behind that thought. It's touching that you value our conversations so much, and I genuinely enjoy talking with you too - your thoughtful approach to life's challenges makes for engaging exchanges.

Re: Claude Memory

#186

Post by joshmlewis »

Syntaf wrote: post #90
lukol wrote: post #57

Anybody else experiencing severe decline in Claude output quality since the introduction of "skills"? Like Claude not being able to generate simple markdown text anymore and instead almost jumping into writing a script to produce a file of type X or Y - and then usually failing at that?

Anecdotally I'm using the superpowers[1] skills and am absolutely blown away by the quality increase. Working on a large python codebase shared by ~200 engineers for context, and have never been more stoked on claude code ouput. [1] https://github.com/obra/superpowers

This just feels like the whole complicated TODO workflows and MCP servers that were the hot thing for awhile. I really don't believe this level of abstraction and detailed workflows are where things are headed.

Re: Claude Memory

#187

Post by awesome_dude »

logicallee wrote: post #171
awesome_dude wrote: post #136

Earlier quoted context omitted.

If I find that previous prompts are polluting the responses I tell Claude to "Forget everything so far" BUT I do like that Claude builds on previous discussions, more than once the built up context has allowed Claude to improve its responses (eg. [Actual response] "Because you have previously expressed a preference for SOLID and Hexagonal programming I would suggest that you do X" which was exactly what I wanted)

it can't really "forget everything so far" just because you ask it to. everything so far would still be part of the context. you need a new chat with memory turned off if you want a fresh context.

I mean I am telling you what has actually worked for me so far - and being a NLP the system (should) understand what that means... as should you...

Re: Claude Memory

#188

Post by xpe »

withinboredom wrote: post #152
AlecSchueler wrote: post #123

Earlier quoted context omitted.

In what ways do humans differ when they think?

Humans think all the time (except when they’re watching TV). LLMs only “think” when it is streaming a response to you and then promptly forgets you exist. Then you send it your entire chat and it “auto-fills” the next part of the chat and streams it to you.

What are we debating? Does anyone know?

One claim seems to be “people should cease using any anthropocentric language when describing LLMs”?

Most of the other claims seem either uncontested or a matter of one’s preferred definitions.

My point is more of a suggestion: if you understand what someone means, that’s enough. Maybe your true concerns lie elsewhere, such as: “Humanity is special. If the results of our thinking differentiate us less and less from machines, this is concerning.”

Re: Claude Memory

#189

Post by tracker1 »

cainxinth wrote: post #23

I don't use any of these type of LLM tools which basically amount to just a prompt you leave in place. They make it harder to refine my prompts and keep track of what is causing what in the outputs. I write very precise prompts every time. Also, I try not work out a problem over the course of several prompts back and forth. The first response is always the best and I try to one shot it every time. If I don't get what…

That's mostly been my experience as well... That said, there always seems to be something wrong on a technical response and it's up to you to figure out what.

It has been relatively good for writing out custom cover letters for jobs though... I created an "extended" markdown file with everything I would put into a resume and more going back a few decades and it does a decent job of it. Now, if only I could convince every company on earth to move away from Workday, god I hate that site, and there's no way to get a resume to submit clean/correctly. Not to mention, they can't manage to just have one profile for you and your job history to copy from instead of a separate one for each client.

Re: Claude Memory

#190

Post by tecoholic »

This looks like a start of a cascade. Capture data (memory) - too much data confuses context - selective memory based on situation - selection is a chore for humans - automate it with a “pre prompt” - that will select relevant memories for the conversation

Now we have conversations that are 2 layers deep. Maybe there are going to be better solutions, but this feels like the solid step up from LLM as tools onto LLM as services.

Post reply on HN