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

81–90 of 326 posts

Re: Claude Memory

#81

Post by spike021 »

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?

it's been doing this since august for me. multiple times instead of using typical cli tools to edit a text file it's tried to write a python script that opens the file, edits it, and saves it. mind-boggling.

it used to consistently use cli tools all the time for these simple tasks.

Re: Claude Memory

#82

Post by jaigupta »

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?

Yes. Noticed in Claude Code after enabling documents skill then had to disable it for this reason.

Re: Claude Memory

#83

Post by wppick »

mstkllah wrote: post #49
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…

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

It's called "prompt engineering", and there's lots of resources on the web about it if you're looking to go deep on it

Re: Claude Memory

#84

Post by AtNightWeCode »

bdangubic wrote: post #75
AtNightWeCode wrote: post #74

How about fixing the most basic things first? Claude is very vulnerable when it comes to injections. Very scary for data processing. How corps dares to use Cloud code is mind-boggling. I mean, you can give Claude simple tasks but if the context is like "Name my cat" it gets derailed immediately no matter what the system prompt is.

“Name my cat” is a very common prompt in corps

It is a test to see if you can break out of the prompt. You have a system prompt like. Bla bla you are a pro AI-translator bla bla bullet points. But then it breaks when the context is like "name my cat" or whatever. It follows those instructions...

Re: Claude Memory

#86

Post by boobsbr »

throitallaway wrote: post #80
amelius wrote: post #5

I'm not sure I would want this. Maybe it could work if the chatbot gives me a list of options before each chat, e.g. when I try to debug some ethernet issues: Please check below: [ ] you are using Ubuntu 18 [ ] your router is at 192.168.1.1 [ ] you prefer to use nmcli to configure your network [ ] your main ethernet interface is eth1 etc. Alternatively, it would be nice if I could say: Please remember that I prefer t…

> you are using Ubuntu 18 Time to upgrade as 18(.04) has been EoL for 2.5+ years!

I'm still running El Capitan: EoL 10 years ago.

Re: Claude Memory

#87

Post by miguelaeh »

> Most importantly, you need to carefully engineer the learning process, so that you are not simply compiling an ever growing laundry list of assertions and traces, but a rich set of relevant learnings that carry value through time. That is the hard part of memory, and now you own that too!

I am interested in knowing more about how this part works. Most approaches I have seen focus on basic RAG pipelines or some variant of that, which don't seem practical or scalable.

Edit: and also, what about procedural memory instead of just storing facts or instructions?

Re: Claude Memory

#88

Post by btown »

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!

Re: Claude Memory

#89

Post by deadbabe »

xpe wrote: post #68
deadbabe wrote: post #17

Earlier quoted context omitted.

That’s creepy, I will promptly turn that off. Also, Claude doesn’t “think” anything, I wish they’d stop with the anthropomorphizations. They are just as bad as hallucinations.

> I wish they’d stop with the anthropomorphizations You mean in how Claude interacts with you, right? If so, you can change the system prompt (under "styles") and explain what you want and don't want. > Claude doesn’t “think” anything Right. LLMs don't 'think' like people do, but they are doing something . At the very least, it can be called information processing.* Unless one believes in souls, that's a fair descrip…

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.

Re: Claude Memory

#90

Post by Syntaf »

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?

Anecdotally I'm using the superpowers[1] skills and am absolutely blown away by the quality increase. Working on a large python codebase shared by ~200 engineers for context, and have never been more stoked on claude code ouput.

[1] https://github.com/obra/superpowers

Post reply on HN