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

241–250 of 326 posts

Re: Claude Memory

#241

Post by Zarathruster »

joshmlewis wrote: post #182
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.

When I first got started with CC, and hadn't given context management too much consideration, I also encountered problems with non-compliance of CLAUDE.md. If you wipe context, CLAUDE.md seems to get very high priority in the next response. All of this is to say that, in addition to the content of CLAUDE.md, context seems to play a role.

Re: Claude Memory

#242

Post by AlecSchueler »

habinero wrote: post #212
AlecSchueler wrote: post #123

Earlier quoted context omitted.

In what ways do humans differ when they think?

Since we have no idea how humans think, that's a pretty unfair and unanswerable question. Humans wrote LLMs, so it's pretty fair to say one is a lot more complex than the other lol

> Humans wrote LLMs, so it's pretty fair to say one is a lot more complex than the other

That's not actually a logical position though is it? And either way I'm not sure "less complex" and "incapable of thought" are the same thing either.

Re: Claude Memory

#243

Post by liqilin1567 »

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…

It really resonates with me, I often run into this situation when I'm trying to fix a bug with llm: if my first prompt is not good enough, then I end up stuck in a loop where I keep asking llm to refine its solution based on the current context.

The result is llm still doesn't output what I want even after 10 rounds of fixing requests.

so I just start a new session and give llm a well-crafted prompt, and suddenly it produce a great result.

Re: Claude Memory

#244

Post by baq »

awesome_dude wrote: post #187
logicallee wrote: post #171

Earlier quoted context omitted.

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...

LLMs literally can’t forget. If it’s in the context window, it is known regardless of what you put in the context next.

That said, if the ‘pretend forget’ you’re getting works for you, great. Just remember it’s fake.

Re: Claude Memory

#245

Post by baq »

imiric wrote: post #154
Nition wrote: post #100

Earlier quoted context omitted.

> 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 init…

> Humans do the same thing. We get stuck on ideas we've already had. Humans usually provide the same answer when asked the same question. LLMs almost never do, even for the exact same prompt. Stop anthropomorphizing these tools.

gpt-5 knows like 5 jokes if you ask it for a joke. That’s close enough to same for me.

Agree on anthropomorphism. Don’t.

Re: Claude Memory

#247

Post by awesome_dude »

baq wrote: post #244
awesome_dude wrote: post #187

Earlier quoted context omitted.

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...

LLMs literally can’t forget. If it’s in the context window, it is known regardless of what you put in the context next. That said, if the ‘pretend forget’ you’re getting works for you, great. Just remember it’s fake.

Like I said, the AI does exactly what I intend for it to do.

Almost, as I said earler, like the AI has processed my request, realised that I am referring to the context of the earlier discussions, and moved on to the next prompt exactly how I have expected it to

Given the two very VERY dumb responses, and multiple people down voting, I am reminded how thankful I am that AI is around now, because it understood what you clearly don't.

I didn't expect it to delete the internet, the world, the universe, or anything, it didn't read my request as an instruction to do so... yet you and that other imbecile seem to think that that's what was meant... even after me saying it was doing as I wanted.

/me shrugs - now fight me how your interpretation is the only right one... go on... (like you and that other person already are)

One thing I am not going to miss is the toxic "We know better" responses from JUNIORS

Re: Claude Memory

#248

Post by mediaman »

awesome_dude wrote: post #187
logicallee wrote: post #171

Earlier quoted context omitted.

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...

He is telling you how it mechanically works. Your comment about it “understanding what that means” because it is an NLP seems bizarre, but maybe you mean it in some other way.

Are you proposing that the attention input context is gone, or that the attention mechanism’s context cost is computationally negated in some way, simply because the system processes natural language? Having the attention mechanism selectively isolate context on command would be an important technical discovery.

Re: Claude Memory

#249

Post by baq »

awesome_dude wrote: post #247
baq wrote: post #244

Earlier quoted context omitted.

LLMs literally can’t forget. If it’s in the context window, it is known regardless of what you put in the context next. That said, if the ‘pretend forget’ you’re getting works for you, great. Just remember it’s fake.

Like I said, the AI does exactly what I intend for it to do. Almost, as I said earler, like the AI has processed my request, realised that I am referring to the context of the earlier discussions, and moved on to the next prompt exactly how I have expected it to Given the two very VERY dumb responses, and multiple people down voting, I am reminded how thankful I am that AI is around now, because it understood what yo…

I think you completely misunderstood me, actually. I explicitly say if it works, great, no sarcasm. LLMs are finicky beasts. Just keep in mind they don’t really forget anything, if you tell it to forget, the things you told it before are still taken into the matrix multiplication mincers and influence outputs just the same. Any forgetting is pretend in that your ‘please forget’ is mixed in after.

But back to scheduled programming: if it works, great. This is prompt engineering, not magic, not humans, just tools. It pays to know how they work, though.

Post reply on HN