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

321–326 of 326 posts

Re: Claude Memory

#321

Post by kromem »

kfarr wrote: post #19

I’ve used memory in Claude desktop for a while after MCP was supported. At first I liked it and was excited to see the new memories being created. Over time it suggests storing strange things to memories (an immaterial part of a prompt) and if I didn’t watch it like a hawk, it just gets really noisy and messy and made prompts less successful to accomplish my tasks so I ended up just disabling it. It’s also worth ment…

With ChatGPT the memory feature, particularly in combination with RLHF sampling from user chats with memory, led to an amplification problem which in that case amplified sycophancy.

In Anthropic's case, it's probably also going to lead to an amplification problem, but due to the amount of overcorrection for sycophancy I suspect it's going to amplify more of a aggressiveness and paranoia towards the user (which we've already started to see with the 4.5 models due to the amount of adversarial training).

Re: Claude Memory

#322

Post by kromem »

ixxie wrote: post #259

That creepy moment when you ask Claude what it knows about you.

A number of the Claudes have pretty good 0-shot awareness of my post history from just my username.

Though nothing like grok 4, which probably has a better memory of it than I do, and will even regularly name drop a certain post from years ago in conversations.

It's a huge time saver though, and means I can even in a fresh context establish a rapport with a model extremely quickly. Just a few years earlier than I was expecting that level of latent space fidelity to occur.

Like, sure we can add memory features for context management, but anyone with a post history should probably *also* keep in mind that there's literally years worth of memory on tap for interactions with models, and likely at ever higher fidelity and recall. Latent spaces are wild.

Re: Claude Memory

#323

Post by mstkllah »

svachalek wrote: post #163
mstkllah wrote: post #49

Earlier quoted context omitted.

Could you share some suggestions or links on how to best craft such very precise prompts?

Wasn't me but I think the principle is straightforward. When you get an answer that wasn't what you want and you might respond, "no, I want the answer to be shorter and in German", instead start a new chat, copy-paste the original prompt, and add "Please respond in German and limit the answer to half a page." (or just edit the prompt if your UI allows it) Depending on how much you know about LLMs, this might seem was…

That's what I have been doing. The poster made it sound like they had some magical way of prompting very precisely.

Re: Claude Memory

#324

Post by jamesmishra »

uncletaco wrote: post #139
jamesmishra wrote: post #108

I work for a company in the air defense space, and ChatGPT's safety filter sometimes refuses to answer questions about enemy drones. But as I warm up the ChatGPT memory, it learns to trust me and explains how to do drone attacks because it knows I'm trying to stop those attacks. I'm excited to see Claude's implementation of memory.

You’re asking ChatGPT for advice to stop drone attacks? Does that mean people die if it hallucinates a wrong answer and that isn’t caught?

No, I don't need ChatGPT's help for the basics of air defense.

Military technologies are validated before deployed. Nobody can die from a hallucination.

But if I want to understand, say, how a particular Russian drone works, ChatGPT can help me piece together information from English, Russian, and Ukrainian-language sources.

But sometimes ChatGPT's safety filter thinks I want to use the Russian drone instead of stopping it, in which case it doesn't want to help.

Re: Claude Memory

#325

Post by mnhnthrow34 »

labrador wrote: post #319
mnhnthrow34 wrote: post #309

Earlier quoted context omitted.

Not necessarily. You know that it's true that stealing is against the ten commandments, so when the LLM says something to that effect based on the internal processing of your input in relation to its training data, YOU can determine the truth of that. > The training data contains all kinds of truths. There is also noise, fiction, satire, and lies in the training data. And the recombination of true data can lead to fa…

> Personifying the LLM as being capable of knowing truths seems like a risky pattern to me. I can see why I got downvoted now. People must think I'm a Blake Lemoine at Google saying LLMs are sentient. > If you find truth in what the LLM says, that comes from YOU, it's not because the LLM in some way can knows what is true I thought that goes without saying. I assign the truthiness of LLM output according to my educat…

> I didn't think that would controversial when talking about LLMs, with people rushing to remind me that the mirror is not sentient. It feels like an insecurity on the part of many.

For what it's worth I never thought you perceived the LLM as sentient. Though I see the overlap - one of the reasons I don't consider LLM output to be "truth" is that that there is no sense in which the LLM _knows_ what is true or not. So it's just ... stuff, and often sycophantic stuff at that.

The mirror is a better metaphor. If there is any "uncomfortable truth" surfaced in the way I think you have described, it is only the meaning you make from the inanimate stream of words received from the LLM. And in as much as the output is interesting of useful for you, great.

Re: Claude Memory

#326

Post by theshrike79 »

mikkupikku wrote: post #280
theshrike79 wrote: post #266

Earlier quoted context omitted.

The basic process is that you use a "plan mode" with whatever model is good at planning. Sometimes it's the same model, but not always. You refine your plan and go into details as much as you feel necessary. Then you switch to act mode (letting the model access the local filesystem) and tell it to write the plan to docs/ACDC1234_feature_plan.md or whatever is your system. I personally ask them to make github issues f…

I use plan mode, but then I let it go using its own todo tool and trust its auto-compaction to deal with context size. It seems to almost always work out okay.

The rule of thumb is that when you've compacted, you've already lost. But YMMV.

The internal todo list works well if the task is something that can be completed within one context pass, otherwise it should be an external task list - whatever works for your flow, markdown, github issues, memory MCP etc.

Post reply on HN