Our next-generation model: Gemini 1.5

Re:Our next-generation model: Gemini 1.5 by behnamoh on Thursday February 15, 2024 @11:30AM (#39384741)

Don't forget that Gemini also has access to the internet, so a lot of RAGging becomes pointless anyway.

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by beppo on Thursday February 15, 2024 @11:41AM (#39384888)

Internet search is a form of RAG, though. 10M tokens is very impressive, but you're not fitting a database, let alone the entire internet into a prompt anytime soon.

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by behnamoh on Thursday February 15, 2024 @11:59AM (#39385113)

You shouldn't fit an entire database in the context anyway.

btw, 10M tokens is 78 times more context window than the newest GPT-4-turbo (128K). In a way, you don't need 78 GPT-4 API calls, only one batch call to Gemini 1.5.

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by cchance on Thursday February 15, 2024 @12:35PM (#39385564)

I don't get this why is it people think that you need to put an entire database in the short-term memory of the AI to be useful? When you work with a DB are you memorizing the entire f*cking database, no, you know the summaries of it and how to access and use it.

People also seem to forget that the average is 1b words that are read by people in their entire LIFETIME, and at 10m, with nearly 100% recall thats pretty damn amazing, i'm pretty sure I don't have perfect recall of 10m words myself lol

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by Qwero on Thursday February 15, 2024 @05:13PM (#39389879)

It increases the use cases.

It can also be a good alternative for fine-tuning.

And the use case of a code base is a good example: if the ai understands the whole context, it can do basically everything.

Let me pay 5€ for a android app rewritten into iOS.

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by choilive on Thursday February 15, 2024 @06:58PM (#39391064)

You certainly don't need that much context for it to be useful, but it definitely opens up a LOT more possibilities without the compromises of implementing some type of RAG. In addition, don't we want our AI to have superhuman capabilities? The ability to work on 10M+ tokens of context at a time could enable superhuman performance in many tasks. Why stop at 10M tokens? Imagine if AI could work on 1B tokens of context like you said?

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by rvnx on Thursday February 15, 2024 @12:29PM (#39385492)

Well it's nice, just sad nobody can use it

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by CharlieDigital on Thursday February 15, 2024 @11:57AM (#39385077)

This may be useful in a generalized use case, but a problem is that many of those results again will add noise.

For any use case where you want contextual results, you need to be able to either filter the search scope or use RAG to pre-define the acceptable corpus.

[ Parent | on HN ]

Re:Our next-generation model: Gemini 1.5 by panarky on Thursday February 15, 2024 @03:33PM (#39388368)

> you need to be able to either filter the search scope or use RAG ...

Unless you can get nearly perfect recall with millions of tokens, which is the claim made here.

[ Parent | on HN ]