Meta Superintelligence Labs' first paper is about RAG • Hacker News Board

Re: Meta Superintelligence Labs' first paper is about RAG

#281

Post by bjornsing » Thu, Oct 16, 2025, 6:52 AM UTC

godelski wrote: post #99

bjornsing wrote: post #77

Earlier quoted context omitted.

Yeah I think this is a general principle. Just look at the quality of US presidents over time, or generations of top physicists. I guess it’s just a numbers game: the number of genuinely interested people is relatively constant while the number of gamers grows with the compensation and perceived status of the activity. So when compensation and perceived status skyrockets the ratio between those numbers changes drasti…

I think the number of generally interested people goes up. Maybe the percent stays the same? But honestly, I think we kill passion for a lot of people. To be cliche, how many people lose the curiosity of a child? I think the cliche exists for a reason. It seems the capacity is in all of us and even once existed.

To some extent I think that’s just human nature, or even animal nature. The optimal explore / exploit tradeoff changes as we age. When we’re children it’s beneficial to explore. As adults it’s often more beneficial to exploit. But you need cultural and organizational safeguards that protect those of us who are more childish and explorative from those that are more cynical and exploitative. Otherwise pursuits of truth aren’t very fruitful.

Re: Meta Superintelligence Labs' first paper is about RAG

#282

Post by danielmarkbruce » Thu, Oct 16, 2025, 3:26 PM UTC

godelski wrote: post #280

danielmarkbruce wrote: post #279

Earlier quoted context omitted.

a - a + a = b when a and b map to the same vector (or in practice, extremely close together). Your assumptions about invertibility etc don't hold in this world.... embeddings are just a bunch of empirically learned coordinates in a dense space. So an example: a maps to [1,2,3] and b maps to [1,2,3] . Again in practice b could map to [1,2,3.0001] or something. To summarize: king, man etc aren't symbols, they get mappe…

man - man + man = woman woman - woman + woman = man => man = woman > Your assumptions about invertibility etc don't hold in this world Yes? Thats what I've said lol. That's what the above example shows. THAT WAS THE ENTIRE POINT > So an example: a maps to [1,2,3] and b maps to [1,2,3] . Again in practice b could map to [1,2,3.0001] or something. >>>>>>>>>> Floating point arithmetic is not associative. I'm glad you fi…

Except you were suggesting it's due to the definition of +, and your silly, irrelevant rant about abstract algebra started when I noted it's plain old addition.

It holds for integers too, floating point arithmetic quirks are irrelevant.

You are applying a bunch of ideas that are irrelevant because you don't have any idea how embedding models actually work.

Re: Meta Superintelligence Labs' first paper is about RAG

#283

Post by shuckles » Fri, Oct 24, 2025, 4:42 AM UTC

CuriouslyC wrote: post #74

shuckles wrote: post #46

Earlier quoted context omitted.

Because she was CTO of OpenAI.

Pretty ironic when access to trade secrets and people skills is seen as more important in a technical field than technical competence.

For the record, I doubt the CTO of OpenAI is the best person to fund if you're looking for trade secrets on training and deploying SOTA LLMs. They are two levels too far from reality to know anything useful.