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

191–200 of 326 posts

Re: Claude Memory

#191

Post by verdverm »

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…

There is some research that supports this approach. Essentially once the LLM starts down a bad path (or gets a little bit of "context poisoning"), it's very hard for it to escape and starting fresh is the way to go

Re: Claude Memory

#192

Post by tecoholic »

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.

Also I am confused by the “wall of exclamation marks”. Is that in the Claude.md file or the Claude Code output? Is that useful in Claude.md? Feels like it’s either going to confuse the LLM or probably just gets stripped.

Re: Claude Memory

#193

Post by labrador »

mnhnthrow34 wrote: post #175
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.

> "the truth sometimes hurts" But it's not the truth in the first place.

The training data contains all kinds of truths. Say I told Claude I was a Christian at some point and then later on I told it I was thinking of stealing office supplies and quitting to start my own business. If Claude said "thou shalt not steal," wouldn't that be true?

Re: Claude Memory

#194

Post by cubefox »

taejavu wrote: post #155
cubefox wrote: post #119

Earlier quoted context omitted.

Anecdotally, LLMs also get less intelligent when the context is filled up with a lot of irrelevant information.

This is well established at this point, it’s called “context rot”: https://research.trychroma.com/context-rot

Yeah, though this paper doesn't test any standard LLM benchmarks like GPQA diamond, SimpleQA, AIME 25, LiveCodeBench v5, etc. So it remains hard to tell how much intelligence is lost when the context is filled with irrelevant information.

Re: Claude Memory

#195

Post by orliesaurus »

Another angle here is data stewardship and transparency...

When a model keeps a running memory of interactions, where is that data going... who has access... how long is it retained...

BUT if the goal is to build trust, more user‑facing controls around memory might help... such as the ability to inspect or reset what the model 'knows'...

ALSO from a performance point of view, memory could be used for caching intermediate representations rather than just storing raw conversation context...

A design‑focused discussion on memory might surface some interesting trade‑offs beyond convenience...

Re: Claude Memory

#196

Post by mudkipdev »

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.

I always just tag the relevant parts of the codebase manually with @ syntax and tell it create this, add unit tests, then format the code and make sure it compiles. There is nothing important enough in my opinion that I have felt the need to create an MD file

Re: Claude Memory

#197

Post by mckn1ght »

cruffle_duffle wrote: post #124
mckn1ght wrote: post #37

Earlier quoted context omitted.

Plan mode is the extent of it for me. It’s essentially prompting to produce a prompt, which is then used to actually execute the inference to produce code changes. It’s really upped the quality of the output IME. But I don’t have any habits around using subagents or lots of CLAUDE.md files etc. I do have some custom commands.

Cursor’s implementation of plan mode works better for me simply because it’s an editable markdown file. Claude code seems to really want to be the driver and you be the copilot. I really dislike that relationship and vastly prefer a workflow that lets me edit the LLM output rather than have it generate some plan and then piss away time and tokens fighting the model so it updates the plan how I want it. With cursor I…

I’ve even resorted to using actual markdown files on disk for long sets of work, as a kind of long term memory meta-plan mode. I’ll even have claude generate them and keep them updated. But I get what you mean.

Re: Claude Memory

#198

Post by astrange »

Feature continues Anthropic's pattern of writing incredibly long system prompts that mostly yell at Claude and have the effect of giving it a nervous breakdown:

https://x.com/janbamjan/status/1981425093323456947

It's smart enough to get thrown off its game by being given obviously mean and contradicting instructions like that.

Re: Claude Memory

#199

Post by gordon_freeman »

chaostheory wrote: post #151
corry wrote: post #27

Earlier quoted context omitted.

Strong agree. For every time that I'd get a better answer if the LLM had a bit more context on me (that I didn't think to provide, but it 'knew') there seems to be a multiple of that where the 'memory' was either actually confounding or possibly confounding the best response. I'm sure OpenAI and Antropic look at the data, and I'm sure it says that for new / unsophisticated users who don't know how to prompt, that thi…

Both of you are missing a lot of use cases. Outside of HN, not everyone uses an LLM for programming. A lot of these people use it as a diary/journal that talks back or as a Walmart therapist.

Walmart therapist?

Re: Claude Memory

#200

Post by ternus »

cruffle_duffle wrote: post #116
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…

I completely agree. ChatGPT put all kinds of nonsense into its memory. “Cruffle is trying to make bath bombs with baking soda and citric acid” or “Cruffle is deciding between a red colored bedsheet or a green colored bedsheet”. Like great both of those are “time bound” and have no relevance after I made the bath bomb or picked a white bedsheet… All these LLM manufacturers lack ways to edit these memories either. It’s…

Were the bath bombs any good? Did the LLM's advice(?) make a meaningful difference? I didn't know making them was so simple.
Post reply on HN