Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A new way to reflect on how you use Claude

anthropic.com

Post reply on HN
Print view View original

51–60 of 61 posts

Re: A new way to reflect on how you use Claude

#51

Post by JamesSwift »

AlexErrant wrote: post #41

> If you can't generate a report, it may be because you don’t have Memory turned on. Has anyone found success with memory and Claude Code? I found Opus's 4.8 memories largely lacking value. Memories are too verbose/specific/yet-generic for the value captured. Instead, I've been holding "retros" with the agent immediately after a session, and _those_ responses have been typically fantastic. It has ideas for coding cha…

Self-directed memories have been awful.

That said, I have had decent success in self-feedback-loop skills. I encapsulate a long process into a skill and the last step is to make changes as needed to the skill itself for things it ran into. I think the isolation of "this specific thing" is what makes it higher signal. Project or god-forbid global memory is just a recipe for hallucinations in my experience.

Re: A new way to reflect on how you use Claude

#52

Post by JamesSwift »

ventana wrote: post #23

I just feel that any attempt of a service I use to summarize and analyze my interactions with it, whether it's the AI tool usage patterns or the music I listened to the most over the past year, makes me feel creepy and makes me want to use the service less. Imagine if your local grocery store came back to you saying that you ate this many chocolate bars over the year. Thanks, I know that you know that, but I don't wa…

https://www.youtube.com/watch?v=Hx7Vv5pqpHg

Re: A new way to reflect on how you use Claude

#54

Post by darepublic »

nottorp wrote: post #31
darepublic wrote: post #27

Earlier quoted context omitted.

How people prompt and the output that ensues is valuable data. So they would probably want variety as a free live experiment.

So a paid product that comes with no documentation, basically.

Not an anthropic fan but in fairness people know how to use it in the most literal sense. Few tools come with documentation on how to use them "well"

Re: A new way to reflect on how you use Claude

#55

Post by skeledrew »

pc86 wrote: post #40
asd88 wrote: post #13

Earlier quoted context omitted.

To be fair, the article doesn’t quite deliver on this promise. The examples are mostly focused on improving work-related workflows, so I guess that’s what they think “daily life” is.

To most of the people working on these AI systems I'm willing to bet work in 90% of their waking life or more.

If someone is doing something like that for 90%+ of their waking life it means it's not work; it's an enjoyable pastime for which they're being paid well.

Re: A new way to reflect on how you use Claude

#56

Post by skeledrew »

empath75 wrote: post #34

I think there's a germ of a good idea here, but really this needs to be data that is presented in a way that encourages human thought and interpretation and not something claude predigests and interprets _for_ you. I found the whole tone as it's executed incredibly off-putting and cringe inducing.

How would you present a collection of your past text conversations that it encourages human thought and interpretation?

Re: A new way to reflect on how you use Claude

#58

Post by xboxnolifes »

MisterTea wrote: post #32
Retr0id wrote: post #26

Earlier quoted context omitted.

I feel this way too except for the music one. The whole reason I use spotify is because I want their algorithm to figure out what music I like.

> ... figure out what music I like. Isn't that something you determine yourself? I listen to a lot of heavy metal because I like it. I also wander around bandcamp and find stuff that isn't heavy metal, but enjoyable, so I buy it. My brain is my algorithm.

Some people enjoy listening to music, not looking for music.

Re: A new way to reflect on how you use Claude

#59

Post by tstrimple »

AlexErrant wrote: post #41

> If you can't generate a report, it may be because you don’t have Memory turned on. Has anyone found success with memory and Claude Code? I found Opus's 4.8 memories largely lacking value. Memories are too verbose/specific/yet-generic for the value captured. Instead, I've been holding "retros" with the agent immediately after a session, and _those_ responses have been typically fantastic. It has ideas for coding cha…

For me, the memory capability is a holding zone for deviations from behavior I'm looking for. I've found that a "retro" after to process "memories" and create CLAUDE.md instructions from them instead works more reliably longer term. I don't do it every session. I've got a separate tool which tracks memories on a per-project basis and recommends when to hold that retro based on accumulated memories.
Post reply on HN