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

Memorizing session transcripts isn't useful

12gramsofcarbon.com

Post reply on HN
Print view View original

21–30 of 168 posts

Re: Memorizing session transcripts isn't useful

#21

Post by dofm »

LPisGood wrote: post #16
dofm wrote: post #9

Blog posts like this just blow me away. > I believed this so strongly that my company built an entire product around this concept. I used to tell folks that "session transcripts were the new oil," that they were more valuable than the code itself. > […] > We don't really write code by hand anymore. Honestly, isn't this just influencer spam? What possible value is there in reading about people who used to have product…

I have to ask: do you still write a lot of code yourself? I and most people I know do not.

I am a freelancer recovering from severe burnout so the answer is a sort of irrelevant no.

I'm trying to rebuild my life so I am in an experimenting and learning phase rather than a massive coding phase, and most of my code work is maintenance of things I have built. That which I do code, I am still coding by hand, though I am dealing with other people's Claude output and I am really unimpressed by it. It's often rather crass.

But I would say to you that if you personally don't write code now but you do have a dependency on one of two presumably unprofitable cloud AI providers, aren't you in trouble? How is this not a three-alarm fire for you?

Re: Memorizing session transcripts isn't useful

#22

Post by grimcompanion »

> I believed this so strongly that my company built an entire product around this concept. I used to tell folks that "session transcripts were the new oil," that they were more valuable than the code itself.

This is infuriatingly common wrt talking/writing about how to use AI effectively. All of the "this is how you write an AGENTS.md" and "you need to talk to it like X to optimize it". Like sure, you can believe that as much as you want but unless you provide some evidence you can keep your shitty CLAUDE.md to yourself and don't pollute the whole company's git repo, thanks.

Re: Memorizing session transcripts isn't useful

#23

Post by dofm »

fortyseven wrote: post #15
dofm wrote: post #9

Blog posts like this just blow me away. > I believed this so strongly that my company built an entire product around this concept. I used to tell folks that "session transcripts were the new oil," that they were more valuable than the code itself. > […] > We don't really write code by hand anymore. Honestly, isn't this just influencer spam? What possible value is there in reading about people who used to have product…

[flagged]

I'm not the Blog Police, I'm a very naughty boy.

I have opinions people apparently don't like, for no subscriber money.

Re: Memorizing session transcripts isn't useful

#24

Post by ungreased0675 »

dofm wrote: post #9

Blog posts like this just blow me away. > I believed this so strongly that my company built an entire product around this concept. I used to tell folks that "session transcripts were the new oil," that they were more valuable than the code itself. > […] > We don't really write code by hand anymore. Honestly, isn't this just influencer spam? What possible value is there in reading about people who used to have product…

It reminds me of the peak crypto days. Lots of resources consumed, many late nights, little to no value created.

Re: Memorizing session transcripts isn't useful

#25

Post by sdesol »

wongarsu wrote: post #8

I agree with the take not to bother with a sophisticated memory system. Anything worth remembering should be in docs, guides, source comments, commit messages or tickets. You don't need another layer, every conceivable granularity is already covered by existing best practices

> You don't need another layer

I do think we need another layer, but it should be a routing layer. I am finalizing my pi-brains extension for Pi (https://github.com/earendil-works/pi) which does this:

https://github.com/gitsense/pi-brains

Right now "humans" need to define the routing rules for how to access information, but I will support what I call "knowledge agents" that can monitor conversations to inject context when needed.

Re: Memorizing session transcripts isn't useful

#26

Post by andai »

LPisGood wrote: post #16
dofm wrote: post #9

Blog posts like this just blow me away. > I believed this so strongly that my company built an entire product around this concept. I used to tell folks that "session transcripts were the new oil," that they were more valuable than the code itself. > […] > We don't really write code by hand anymore. Honestly, isn't this just influencer spam? What possible value is there in reading about people who used to have product…

I have to ask: do you still write a lot of code yourself? I and most people I know do not.

I force myself to do it at least once a week, you know, like cardio. Keeps the doctor away.

Re: Memorizing session transcripts isn't useful

#28

Post by andai »

dofm wrote: post #21
LPisGood wrote: post #16

Earlier quoted context omitted.

I have to ask: do you still write a lot of code yourself? I and most people I know do not.

I am a freelancer recovering from severe burnout so the answer is a sort of irrelevant no. I'm trying to rebuild my life so I am in an experimenting and learning phase rather than a massive coding phase, and most of my code work is maintenance of things I have built. That which I do code, I am still coding by hand, though I am dealing with other people's Claude output and I am really unimpressed by it. It's often rat…

Worst case scenario you just switch to a free model, which are 2025-ish in quality.

Re: Memorizing session transcripts isn't useful

#29

Post by andai »

throwup238 wrote: post #14
wongarsu wrote: post #8

I agree with the take not to bother with a sophisticated memory system. Anything worth remembering should be in docs, guides, source comments, commit messages or tickets. You don't need another layer, every conceivable granularity is already covered by existing best practices

Especially a layer that is largely out of band in a project (i.e. ~/.claude/…). In any project where I’ve needed memory I just add a line to AGENTS.md telling it to use MEMORY.md to save memories or STATUS.md to track progress.

I've been enjoying having a little todo file the agent updates as it goes along, because then I can keep track of progress without scrolling through aeons of "Combobulating..."

Also if context runs out you can just do "cat todo.md | agent" and you're off to the races again.

Re: Memorizing session transcripts isn't useful

#30

Post by syntheticcdo »

aranw wrote: post #12

t once had to tell claude 3-4 times to stop assuming the state of a system was the way it kept iterating it was cause it was in it's memory. I repeatably told it to otherwise and it just never updated it's memory and instead kept referencing it's memory about the state of a particular system

Did you try to delete the memory yourself?
Post reply on HN