Google Titans Model Explained: The Future of Memory-Driven AI Architectures

FWIW, Phil Wang (lucidrains) has been working on Titans reimplementation since roughly the day the paper was released. It looks to me from the repository that some of the paper's claims have not been reproduced yet, and reading between the lines, it might be Wang considers the paper to not be that groundbreaking after all -- hard to say definitively but the commit speed has definitely slowed down, and the last comments involve failing to replicate some of the key claims.

Unfortunately. The paper looks really good, and I'd like for it to be true.

https://github.com/lucidrains/titans-pytorch

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#5

Post by wstrange » Fri, Feb 21, 2025, 11:50 PM UTC

For those of you in the field, this seems like a big deal? ELI5

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#6

Post by mattigames » Fri, Feb 21, 2025, 11:51 PM UTC

ajcp wrote: post #3

> opening doors to innovations in AI-driven reasoning, healthcare, and beyond. You went with "healthcare"?

It's Google, so it means healthcare as in the business not the practice, "help me squeeze more money out of people that desperately need this medicine to survive"

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#7

Post by bglazer » Sat, Feb 22, 2025, 12:07 AM UTC

This article gives off really strong chatgpt vibes. Bullet points! Confidently stated but quite vague statements! Integration, key innovations, more bullet points! Distinct lack of personal viewpoints or unique opinions! Very long!

Maybe I’m being uncharitable and this is just the way things are written on Medium, but man this was not an easy or particularly enlightening read.

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#8

Post by llm_trw » Sat, Feb 22, 2025, 12:14 AM UTC

wstrange wrote: post #5

For those of you in the field, this seems like a big deal? ELI5

I don't know. Google has some great papers but a lot more hot air. The best thing to do when you see a google paper is ignore it until someone you trust more writes a second paper about it.

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#9

Post by daedrdev » Sat, Feb 22, 2025, 12:48 AM UTC

wstrange wrote: post #5

For those of you in the field, this seems like a big deal? ELI5

Their model on protein folding was obviously very impactful. Their model for new chemicals has to my understanding provided no value. Based on this track record, who knows.

Re: Google Titans Model Explained: The Future of Memory-Driven AI Architectures

#10

Post by sky2224 » Sat, Feb 22, 2025, 12:53 AM UTC

bglazer wrote: post #7

This article gives off really strong chatgpt vibes. Bullet points! Confidently stated but quite vague statements! Integration, key innovations, more bullet points! Distinct lack of personal viewpoints or unique opinions! Very long! Maybe I’m being uncharitable and this is just the way things are written on Medium, but man this was not an easy or particularly enlightening read.

Nah it's definitely AI generated. I used to like Medium a lot, but ever since AI Models became mainstream, it's just been a cesspool of horribly written articles.