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

151–160 of 326 posts

Re: Claude Memory

#151

Post by chaostheory »

corry wrote: post #27
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…

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.

Re: Claude Memory

#152

Post by withinboredom »

AlecSchueler wrote: post #123
deadbabe wrote: post #89

Earlier quoted context omitted.

When you type a calculation into a calculator and it gives you an answer, do you say the calculator thinks of the answer? An LLM is basically the same as a calculator, except instead of giving you answers to math formulas it gives you a response to any kind of text.

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.

Re: Claude Memory

#153

Post by svachalek »

mbesto wrote: post #103
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…

> For every time that I'd get a better answer if the LLM had a bit more context on me If you already know what a good answer is why use a LLM? If the answer is "it'll just write the same thing quicker than I would have", then why not just use it as an autocomplete feature?

You don't need to know what the answer is ahead of time to recognize the difference between a good answer and a bad answer. Many times the answer comes back as a Python script and I'm like, oh I hate Python, rewrite that. So it's useful to have a permanent prompt that tells it things like that.

But myself as well, that prompt is very short. I don't keep a large stable of reusable prompts because I agree, every unnecessary word is a distraction that does more harm than good.

Re: Claude Memory

#154

Post by imiric »

Nition wrote: post #100
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 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.

Re: Claude Memory

#155

Post by taejavu »

cubefox wrote: post #119
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…

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

Re: Claude Memory

#158

Post by svachalek »

jasonjmcghee wrote: post #147
stingraycharles wrote: post #111

Earlier quoted context omitted.

Yes, your last paragraph is absolutely the key to great output: instead of entering a discussion, refine the original prompt. It is much more token efficient, and gets rid of a lot of noise. I often start out with “proceed by asking me 5 questions that reduce ambiguity” or something like that, and then refine the original prompt. It seems like we’re all discovering similar patterns on how to interact with LLMs the be…

The trick to do this well is to split the part of the prompt that might change and won't change. So if you are providing context like code, first have it read all of that, then (new message) give it instructions. This way that is written to the cache and you can reuse it even if you're editing your core prompt. If you make this one message, it's a cache miss / write every time you edit. You can edit 10 times for the…

Is Claude caching by whole message only? Pretty sure OpenAI caches up to the first differing character.

Re: Claude Memory

#159

Post by svachalek »

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.

That is odd, are you using small models with the temperature cranked up? I mean I'm not getting word for word the same answer but material differences are rare. All these rising benchmark scores come from increasingly consistent and correct answers.

Perhaps you are stuck on the stochastic parrot fallacy.

Re: Claude Memory

#160

Post by ankit219 »

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 for reference) is what these models are RLd on, so works better.
Post reply on HN