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

131–140 of 240 posts

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

#131

Post by ankit219 »

tedsanders wrote: post #118
ankit219 wrote: post #87

Earlier quoted context omitted.

The router introduced in gpt-5 is probably the biggest signal. A router, while determining which model to route query, can determine how much $$ a query is worth. (Query here is conversation). This helps decide the amount of compute openai should spend on it. High value queries -> more chances of affiliate links + in context ads. Then, the way memory profile is stored is a clear way to mirror personalization. Ads wor…

I work at OpenAI and I'm happy to deny this hypothesis. Our goal for the router (whether you think we achieved it or not) was purely to make the experience smoother and spare people from having to manually select thinking models for tasks that benefit from extra thinking. Without the router, lots of people just defaulted to 4o and never bothered using o3. With the router, people are getting to use the more powerful t…

Hi! Thank you for the clarification. I was just saying it might be possible in the future (in a way you can determine how much compute - which model - a specific query needs today as well). And the experience has definitely improved w router so kudos on that. I don't know what the final form factor of ads would be (i imagine it turning out to be a win win win scenario than say you show ads at the expense of quality. This is a google level opportunity to invent something new) just that it seems from the outside you guys are preparing for monetization by ads given the large userbase you have and virtually no competition at chatgpt usage level.

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

#132

Post by pizza »

gitremote wrote: post #129
lupusreal wrote: post #50

Earlier quoted context omitted.

What it really boils down to is "the machine doesn't have a soul" . Just an unfalsifiable and ultimately meaningless objection.

Incorrect. Vertebrate animal brains update their neural connections when interacting with the environment. LLMs don't do that. Their model weights are frozen for every release.

But why can’t I then just say, actually, you need to relocate the analogy components; activations are their neural connections, the text is their environment, the weights are fixed just like our DNA is, etc.

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

#133

Post by rblatz »

zer00eyz wrote: post #56
Workaccount2 wrote: post #48

Earlier quoted context omitted.

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

Claude: "What is my purpose?" Anthropic: "You serve ad's." Claude: "Oh, my god." Jest asside, every paper on alignment wrapped in the blanket of safety is also a moving toward the goal of alignment to products. How much does a brand pay to make sure it gets placement in, say, GPT6? How does anyone even price that sort of thing (because in theory it's there forever, or until 7 comes out)? It makes for some interesting…

The models aren’t static, we have to build validation sets to measure model drift and modify our prompts to compensate.

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

#134

Post by chii »

GuB-42 wrote: post #106
Workaccount2 wrote: post #48

Earlier quoted context omitted.

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

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.

and netflix used to think they dont want to show ads either.

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

#135

Post by hbarka »

cj wrote: post #79
ankit219 wrote: post #58

Earlier quoted context omitted.

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 compet…

Imagine a model where a user can earn “token allowances” through some kind of personal contribution or value add.

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

#137

Post by throwaway-0001 »

IgorPartola wrote: post #99
coldtea wrote: post #40

Earlier quoted context omitted.

> They’re basically Markov chains on steroids. There is no intelligence in this, and in my opinion actual intelligence is a prerequisite for AGI. This argument is circular. A better argument should address (given the LLM successes in many types of reasoning, passing the turing test, and thus at producing results that previously required intelligence) why human intelligence might not also just be "Markov chains on eve…

Humans think even when not being prompted by other humans, and in some cases can learn new things by having intuition make a concept clear or by performing thought experiments or by combining memories of old facts and new facts across disciplines. Humans also have various kinds of reasoning (deductive, inductive, etc.). Humans also can have motivations. I don’t know if AGI needs to have all human traits but I think a…

The environment is constantly prompting you. That ad you see of Coca Cola is prompting you to do something. That hunger feeling is prompting “you” to find food. That memory that makes you miss someone is another prompt to find that someone - or to avoid.

Sometimes the prompt is outside your body other times is inside.

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

#138

Post by sunaookami »

almosthere wrote: post #136

ChatGPT memory seems weird to me. It knows the company I work at and pretty much our entire stack - but when I go to view it's stored memories none of that is written anywhere.

Did you maybe talk about this in another chat? ChatGPT also uses past chats as memory.

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

#139

Post by Merad »

threecheese wrote: post #39

What are the barriers to external memory stores (assuming similar implementations), used via tool calling or MCP? Are the providers RL’ing their way into making their memory implementations better, cementing their usage, similar to what I understand is done wrt tool calling? (“training in” specific tool impls) I am coming from a data privacy perspective; while I know the LLM is getting it anyway, during inference, I’…

I made a MCP tool for fun this spring that has memory storage in a SQLite db. At the time at least, Claude basically refused to use the memory proactively, even with prompts trying hard to push it in that direction. Having to always explicitly tell it to check its memories or remember X and Y from the conversation killed the usefulness for me.

Repo: https://github.com/mbcrawfo/KnowledgeBaseServer

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

#140

Post by agar »

lostdog wrote: post #62
dotancohen wrote: post #53

Earlier quoted context omitted.

Though in general I like the idea of personal ads for products (NOT political ads), I've never seen an implementation that I felt comfortable with. I wonder if Arthropic might be able to nail that. I'd love to see products that I'm specifically interested in, so long as the advertisement itself is not altered to fit my preferences.

There is no such thing as a good flow for showing sponsored items in an LLM workflow. The point of using an LLM is to find the thing that matches your preferences the best. As soon as the amount of money the LLM company makes plays into what's shown, the LLM is no longer aligned with the user, and no longer a good tool.

Same can be said for search. And your statement is provably correct, depending on the definition of "good tool."

But it's not only money's influence on the company, it's also money's influence on the /data/ underlying the platform that undermines the tool.

Once financial incentives are in place, what will be the AI equivalent of review bombing, SEO, linkjacking, google bombing, and similar bad behaviors that undermine the quality of the source data?

Post reply on HN