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

Claude’s memory architecture is the opposite of ChatGPT’s

shloked.com

Post reply on HN
Print view View original

71–80 of 240 posts

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#71

Post by dgfitz »

0xCMP wrote: post #64
withinboredom wrote: post #60

Earlier quoted context omitted.

It can’t learn or think unless prompted, then it is given a very small slice of time to respond and then it stops. Forever. Any past conversations are never “thought” of again. It has no intelligence. Intelligence implies thinking and it isn’t doing that. It’s not notifying you at 3am to say “oh hey, remember that thing we were talking about. I think I have a better solution!” No. It isn’t thinking. It doesn’t unders…

Just because it's not independent and autonomous does not mean it could not be intelligent. If existing humans minds could be stopped/started without damage, copied perfectly, and had their memory state modified at-will would that make us not intelligent?

> Just because it's not independent and autonomous does not mean it could not be intelligent.

So to rephrase: it’s not independent or autonomous. But it can still be intelligent. This is probably a good time to point out that trees are independent and autonomous. So we can conclude that LLMs are possibly as intelligent as trees. Super duper.

> If existing humans minds could be stopped/started without damage, copied perfectly, and had their memory state modified at-will would that make us not intelligent?

To rephrase: if you take something already agreed to as intelligent, and changed it, is it still intelligent? The answer is, no damn clue.

These are worse than weak arguments, there is no thesis.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#72

Post by biophysboy »

spongebobstoes wrote: post #59
ankit219 wrote: post #37

The difference is implementation comes down to business goals more than anything. There is a clear directionality for ChatGPT. At some point they will monetize by ads and affiliate links. Their memory implementation is aimed at creating a user profile. Claude's memory implementation feels more oriented towards the long term goal of accessing abstractions and past interactions. It's very close to how humans access mem…

why do you see a "clear directionality" leading to ads? this is not obvious to me. chatgpt is not social media, they do not have to monetize in the same way they are making plenty of money from subscriptions, not to count enterprise, business and API

Presumably they would offer both models (ads & subscriptions) to reach as many users as possible, provided that both models are net profitable. I could see free versions having limits to queries per day, Tinder style.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#73

Post by notahacker »

jmcgough wrote: post #49
creata wrote: post #19

Earlier quoted context omitted.

> As I understand them, LLMs right now don’t understand concepts. In my uninformed opinion it feels like there's probably some meaningful learned representation of at least common or basic concepts. It just seems like the easiest way for LLMs to perform as well as they do.

Humans assume that being able to produce meaningful language is indicative of intelligence, because the only way to do this until LLMs was through human intelligence.

Yep. Although the average human also considered proficiency in mathematics to be indicative of intelligence until we invented the pocket calculator, so maybe we're just not smart enough to define what intelligence is.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#74

Post by amannm »

> Anthropic's more technical users inherently understand how LLMs work.

Yes, I too imagine these "more technical users" spamming rocketship and confetti emojis absolutely _celebrating_ the most toxic code contributions imaginable to some of the most important software out there in the world. Claude is the exact kind of engineer (by default) you don't want in your company. Whatever little reinforcement learning system/simulation they used to fine-tune their model is a mockery of what real software engineering is.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#75

Post by coldtea »

shakna wrote: post #57
coldtea wrote: post #46

Earlier quoted context omitted.

> For one thing, I have internal state that continues to exist when I'm not responding to text input Do you? Or do you just have memory and are run on a short loop?

Whilst all the choices you make tend to be in the grey matter, the rest of you does have internal state - mostly in your white matter. https://scisimple.com/en/articles/2025-03-22-white-matter-a-...

>Whilst all the choices you make tend to be in the grey matter, the rest of you does have internal state - mostly in your white matter.

Yeah, but so? Does the substrate of the memory ...matter? (pun intended)

When I wrote memory above it could refer to all the state we keep, regardless if it's gray matter, white matter, the gut "second brain", etc.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#76

Post by degamad »

codedokode wrote: post #35
modeless wrote: post #9

The link to the breakdown of ChatGPT's memory implementation is broken, the correct link is: https://www.shloked.com/writing/chatgpt-memory-bitter-lesson This is really cool, I was wondering how memory had been implemented in ChatGPT. Very interesting to see the completely different approaches. It seems to me like Claude's is better suited for solving technical tasks while ChatGPT's is more suited to improving casual…

You don't want an AGI. How do you make it obey?

The same way you make the other smart people in your social group obey?

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#77

Post by recursive »

omnicognate wrote: post #8
kiitos wrote: post #5

> Anthropic's more technical users inherently understand how LLMs work. good (if superficial) post in general, but on this point specifically, emphatically: no, they do not -- no shade, nobody does, at least not in any meaningful sense

Understanding how they work in the sense that permits people to invent and implement them, that provides the exact steps to compute every weight and output, is not "meaningful"? There is a lot left to learn about the behaviour of LLMs, higher-level conceptual models to be formed to help us predict specific outcomes and design improved systems, but this meme that "nobody knows how LLMs work" is out of control.

None of that is inherent, and vanishingly few of Anthropic's users invented LLMs.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#78

Post by recursive »

bhhaskin wrote: post #52
ForHackernews wrote: post #21

Earlier quoted context omitted.

For one thing, I have internal state that continues to exist when I'm not responding to text input; I have some (limited) access to my own internal state and can reason about it (metacognition). So far, LLMs do not, and even when they claim they are, they are hallucinating https://transformer-circuits.pub/2025/attribution-graphs/bio...

I completely agree. LLMs only do call and response. Without the call there is no response.

Would a human born into a sensory deprivation chamber ever make a call?

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#79

Post by cj »

ankit219 wrote: post #58
Workaccount2 wrote: post #48

Earlier quoted context omitted.

Don't fool yourself into thinking Anthropic won't be serving up personalized ads too.

My conjecture is that their memory implementation is not aimed at building a user profile. I don't know if they would or would not serve ads in the future, but it's hard to see how the current implementation helps them in that regard.

> I don't know if they would or would not serve ads in the future

There are 2 possible futures:

1) You are served ads based on your interactions

2) You pay a subscription fee equal to the amount they would have otherwise earned on ads

I highly doubt #2 will happen. (See: Facebook, Google, twitter, et al)

Let’s not fool ourselves. We will be monetized.

And model quality will be degraded to maximize profits when competition in the LLM space dies down.

It’s not a pretty future. I wouldn’t be surprised if right now is the peak of model quality, etc. Peak competition, everyone is trying to be the best. That won’t continue forever. Eventually everyone will pivot their priority towards monetization rather than model quality/training.

Hopefully I’m wrong.

Re: Claude’s memory architecture is the opposite of ChatGPT’s

#80

Post by astrange »

sixo wrote: post #16
SweetSoftPillow wrote: post #15

Earlier quoted context omitted.

What is "actual intelligence" and how are you different from a Markov chain?

Roughly, actual intelligence needs to maintain a world model in its internal representation, not merely an embedding of language, which is a very different data structure and probably will be learned in a very different way. This includes things like: - a map of the world, or concept space, or a codebase, etc - causality - "factoring" which breaks down systems or interactions into predictable parts Language alone is…

> Roughly, actual intelligence needs to maintain a world model in its internal representation

This is GOFAI metaphor-based development, which never once produced anything useful. They just sat around saying things like "people have world models" and then decided if they programmed something and called it a "world model" they'd get intelligence, it didn't work out, but then they still just went around claiming people have "world models" as if they hadn't just made it up.

An alternative thesis "people do things that worked the last time they did them" explains both language and action planning better; eg you don't form a model of the contents of your garbage in order to take it to the dumpster.

https://www.cambridge.org/core/books/abs/computation-and-hum...

Post reply on HN