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

191–200 of 240 posts

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

#191

Post by PxldLtd »

stickfigure wrote: post #115
techbruv wrote: post #22

Earlier quoted context omitted.

I don’t understand the argument “AI is just XYZ mechanism, therefore it cannot be intelligent”. Does the mechanism really disqualify it from intelligence if behaviorally, you cannot distinguish it from “real” intelligence? I’m not saying that LLMs have certainly surpassed the “cannot distinguish from real intelligence” threshold, but saying there’s not even a little bit of intelligence in a system that can solve more…

> if behaviorally, you cannot distinguish it from “real” intelligence? Current LLMs are a long way from there. You may think "sure seems like it passes the Turing test to me!" but they all fail if you carry on a conversation long enough. AIs need some equivalent of neuroplasticity and as of yet they do not have it.

This is what I think is the next evolution of these models. Our brains are made up of many different types of neurones all interspersed with local regions made up of specific types. From my understanding most approaches to tensors don't integrate these different neuronal models at the node level; it's usually by feeding several disparate models data and combining an end result. Being able to reshape the underlying model and have varying tensor types that can migrate or have a lifetime seems exciting to me.

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

#192

Post by Geezus_42 »

fluidcruft wrote: post #119
cj wrote: post #95

Earlier quoted context omitted.

If that’s the case, we have an even bigger problem on our hands. How will these companies ever be profitable? If we’re already paying $20/mo and they’re operating at a loss, what’s the next move (assuming we’re only worth an extra $300/yr with ads?) The math doesn’t add up, unless we stop training new models and degrade the ones currently in production, or have some compute breakthrough that makes hardware + operatin…

Well to make things worse I was pretty convinced those were faked numbers to push the TilTok ban forward. I really doubt Meta and Google are each taking in this much per user. But my point is more that even if it were that high, ChatGPT isn't going to capture all the engagement. And even then I don't know whether $300 is much particularly after subtracting operating overhead. I'm just saying I have trouble believing…

Everything devolves into ADs eventually. Why would productized LLMs be any different?

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

#193

Post by Geezus_42 »

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

None of the "AI" companies are profitable currently. Everything devolves into selling ADs eventually. What makes you think LLMs are special?

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

#194

Post by FergusArgyll »

FooBarWidget wrote: post #188
rkomorn wrote: post #182

Earlier quoted context omitted.

This leaves me somewhere between surprised and shocked.

Maybe you shouldn't be. The ad-hating paranoid HN user is not representative of the general population. Probably the exact opposite, in fact. My wife and mother love ads, they are always on the hunt for the latest good deals and love discount shopping. When I tried to remove the ads on their computers or in the postal mail, they protested. I think they are far more representative of the general population.

Yeah, I've encountered more than one person who didn't want me to install ublock origin for them because "Then I won't see any ads".

People have different preferences ¯\_(ツ)_/¯

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

#195

Post by FergusArgyll »

mrheosuper wrote: post #126
GuB-42 wrote: post #106

Earlier quoted context omitted.

Anthropic seems to want to make you buy a subscription, not show you ads. ChatGPT seems to be more popular to those who don't want to pay, and they are therefore more likely to rely on ads.

so ChatGPT will become "saleman". And i do not trust any saleman.

The plan is not ads said by chatgpt - it's ads on the side that are relevant to the conversartion (or you in general). Or affiliate links. That's my understanding.

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

#196

Post by aswegs8 »

__MatrixMan__ wrote: post #183
mrheosuper wrote: post #126

Earlier quoted context omitted.

so ChatGPT will become "saleman". And i do not trust any saleman.

They're all salesmen, they were trained on the web which is jam packed with SEO content.

Interesting point. Never thought about AI slop being fed by SEO slop.

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

#197

Post by Tistron »

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 would their way of handling memory for conversations have much to do with how they will analyse your user profile for ads? They have access to all your history either way and can use that to figure out what products to recommend, or ads to display, no?

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

#198

Post by anticrymactic »

ornornor wrote: post #18
SweetSoftPillow wrote: post #15

Earlier quoted context omitted.

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

What I mean is that the current generation of LLMs don’t understand how concepts relate to one another. Which is why they’re so bad at maths for instance. Markov chains can’t deduce anything logically. I can.

> Which is why they’re so bad at maths for instance.

I don't think LLMs currently are intelligent. But please show a GPT-5 chat where it gets any math problem wrong, that most "intelligent" people would get right.

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

#199

Post by BigGreenJorts »

lupusreal wrote: post #186
lodovic wrote: post #145

Earlier quoted context omitted.

I find that hard to believe. As long as we have open weight models, people will have an alternative to these subscriptions. For $200 a month it is cheaper to buy a GPU with lots of memory or rent a private H200. No ads and no spying. At this point the subscriptions are mainly about the agent functionality and not so much the knowledge in the models themselves.

I think what you're missing here is most OpenAI users aren't technical in the slightest. They have massive and growing adoption from the general public. The general public buy services, not roll their own for free, and they even prefer to buy service from the brand they know over getting cheaper service from somebody else.

The conclusion I got from their comment was that the highest margin tier (the business customers) would be incentivized to build their own service instead of paying the subscription. Of course, I am doubtful that for the vast majority of businesses this viable/at all more cost effective when a service AWS is highly popular and extremely profitable.

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

#200

Post by thinkingtoilet »

OsrsNeedsf2P wrote: post #51
thinkingtoilet wrote: post #36

Earlier quoted context omitted.

It's funny, I can't get ChatGPT to remember basic things at all. I'm using it to learn a language (I tried many AI tutors and just raw ChatGPT was the best by far) and I constantly have to tell it to speak slowly. I will tell it to remember this as a rule and to do this for all our conversations but it literally can't remember that. It's strange. There are other things too.

How do you use it to learn languages? I tried using it to shadow speaking, but it kept saying I was repeating it back correctly (or "mostly correctly"), even when I forgot half the sentence and was completely wrong

I use it a couple ways. I am learning Hindi and while it's the third most spoken language in the world there really isn't that many resources for learning it. Sites like Babel don't have a Hindi course. I started with Pimsleur which is by far the best resource out there. It's mix of vocab and conversation done in an incredibly effective way. They only have two levels for Hindi so it's not a lot. With that base I use ChatGPT in the following ways.

- With the new GPT Voice, I have basic, planned conversations. Let's go to a restaurant. Let's say we're friends who ran into each other. etc...

- I use it for quizzes. "Let's work on these verbs in these tenses. Come up with a quiz randomly selecting a verb and a tense and ask me to say real world sentences." "Quiz me on the numbers one through twenty".

- I am using it to help learn the Hindi script. I ask it to write childrens stories for me, but I ask it to write each line in the hindi script, then phonetic spelling of the hindi script, and then in english so I can scroll down and see only the hindi first, then if I have issues I can see the phonetic spelling of the hindi. Then I can try to translate it and then check the english translation on the third line.

Those are the main things I'm doing. I don't know if I'll ever be fluent, but I find if you work on these basic ever day conversations you can have a conversation with someone. If you speak a language for the first time around a native speaker it's usually very predictable. They'll ask how long you've been learning, where did you learn, have you been to , and you can direct the conversation by saying things about where you live and your family, etc... That's the base I'm building and it's fun. If you're not doing at least 30 minutes a day you're never going to learn a language, you probably need an hour more a day to really get fluent.

Post reply on HN