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

91–100 of 326 posts

Re: Claude Memory

#91

Post by bongodongobob »

labrador wrote: post #79
teeklp wrote: post #71

Earlier quoted context omitted.

This is literally insane.

I love that people hate this because that means I'm using AI in an interesting way. People will see what I mean eventually. Edit: I see the confusion. OP is talking about needing precise output for agents. I'm talking about riffing on ideas that may go in strange places.

No, he's talking about memory getting passed into the prompts and maintaining control. When you turn on memory, you have no idea what's getting stuffed into the system prompt. This applies to chats and agents. He's talking about chat.

Re: Claude Memory

#92

Post by st-msl »

btown wrote: post #88
st-msl wrote: post #77

[dead]

For anyone skimming rapidly through the thread who might have been confused here, especially since it's worded in similar ways that someone might reply to a mention of their own work on HN: the parent is not associated with Claude, but is the founder of a separate startup: https://www.memco.ai/ Both are exciting approaches, but with notably different use cases in mind!

Thanks btown, I updated the first sentence to make that clear. Nice work btw

Re: Claude Memory

#93

Post by giancarlostoro »

saratogacx wrote: post #33
giancarlostoro wrote: post #22

Earlier quoted context omitted.

Perplexity and Grok have had something like this for a while where you can make a workspace and write a pre-prompt that is tacked on before your questions so it knows that I use Arch instead of Ubuntu. The nice thing is you can do this for various different workspaces (called different things across different AI providers) and it can refine your needs per workspace.

Claude has this by way of projects, you can set instructions that act as a default starting prompt for any chats in that project. I use it to describe my project tech stack and preferences so I don't need to keep re-hashing it. Overall it has been a really useful feature to maintaining a high signal/noise ratio. In Github Copilot's web chat it is personal instructions or spaces (Like perplexity), In CoPilot (M365) th…

Thank you, I am just now getting into Claude and Claude Code, it seems I need to learn more about the nuances for Claude Code.

Re: Claude Memory

#94

Post by antihipocrat »

ivape wrote: post #56
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…

Regardless, whatever memory engines people come up with, it's not in anyone's interest to have the memory layer sitting on Anthropic or Open AIs server. The memory layer should exist locally, with these external servers acting as nothing else but LLM request fulfillment. Now, we'll never be able to educate most of the world on why they should seek out tools that handle the memory layer locally, and these big companie…

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.

Re: Claude Memory

#95

Post by josefresco »

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?

Not since skills but earlier as others have said I've noticed Claude chat seems to create tools to create the output I need instead of just doing it directly. Obviously this is a cost saving strategy, although I'm not sure how the added compute of creating an entire reusable tool for a simple one-time operation helps but hey what do I know?

Re: Claude Memory

#96

Post by labrador »

bongodongobob wrote: post #91
labrador wrote: post #79

Earlier quoted context omitted.

I love that people hate this because that means I'm using AI in an interesting way. People will see what I mean eventually. Edit: I see the confusion. OP is talking about needing precise output for agents. I'm talking about riffing on ideas that may go in strange places.

No, he's talking about memory getting passed into the prompts and maintaining control. When you turn on memory, you have no idea what's getting stuffed into the system prompt. This applies to chats and agents. He's talking about chat.

Parent is not chatting though. Parent is crafting a precise prompt. I agree, in that case you don't want memory to introduce global state.

I see the distinction between two workflows: one where you need deterministic control and one where you want emergent, exploratory conversation.

Re: Claude Memory

#97

Post by ivape »

antihipocrat wrote: post #94
ivape wrote: post #56

Earlier quoted context omitted.

Regardless, whatever memory engines people come up with, it's not in anyone's interest to have the memory layer sitting on Anthropic or Open AIs server. The memory layer should exist locally, with these external servers acting as nothing else but LLM request fulfillment. Now, we'll never be able to educate most of the world on why they should seek out tools that handle the memory layer locally, and these big companie…

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 vendors know there is much more money in saving your thoughts.

Privacy-first intelligence requires these two things at the bare minimum:

1) Your thoughts stay on your device

2) At worst, your thoughts pass through a no-logging environment on the server. Memory cannot live here because any context saved to a db is basically just logging.

3) Or slightly worse, your local memory agent only sends some prompts to a no-logging server.

The first two things will never be offered by the current megacapitalist.

Finally, the developer community should not be adopting things like Claude memory because we know. We’re not ignorant of the implications compared to non-technical people. We know what this data looks like, where it’s saved, how it’s passed around, and what it could be used for. We absolutely know better.

Re: Claude Memory

#98

Post by indigodaddy »

I don't think they addressed it in the article, but what is the scope of infrastructure cost/addition for a feature such as this? Sounds like a pretty significant/high one to me. I'd imagine they would have to add huge multiple clusters of very high-memory servers to implement a (micro?)service such as this?

Re: Claude Memory

#100

Post by Nition »

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…

> The first response is always the best and I try to one shot it every time. If I don't get what I want, I adjust the prompt and try again.

I've really noticed this too and ended up taking your same strategy, especially with programming questions.

For example if I ask for some code and the LLM initially makes an incorrect assumption, I notice the result tends to be better if I go back and provide that info in my initial question, vs. clarifying in a follow-up and asking for the change. The latter tends to still contain some code/ideas from the first response that aren't necessarily needed.

Humans do the same thing. We get stuck on ideas we've already had.[1]

---

[1] e.g. Rational Choice in an Uncertain World (1988) explains: "Norman R. F. Maier noted that when a group faces a problem, the natural tendency of its members is to propose possible solutions as they begin to discuss the problem. Consequently, the group interaction focuses on the merits and problems of the proposed solutions, people become emotionally attached to the ones they have suggested, and superior solutions are not suggested. Maier enacted an edict to enhance group problem solving: 'Do not propose solutions until the problem has been discussed as thoroughly as possible without suggesting any.'"

Post reply on HN