Тёмный

How Google is Expanding the Gemini Era 

Sam Witteveen
Подписаться 61 тыс.
Просмотров 4,2 тыс.
50% 1

In this first of 3 vids covering Google I/O 2024 I go through the new announcements around Gemini and products using it.
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: drp.li/dIMes
👨‍💻Github:
github.com/samwit/langchain-t... (updated)
git hub.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
01:24 Gemini Era
02:07 Gemini is in every Google Product
02:30 Gemini App
02:51 Gemini Advanced
03:01 Gemini Advanced Now Use Gemini 1.5 Pro with 1M Context
03:46 Google Gemini 1.5 Pro Model with 2M Tokens
04:24 NotebookLM with 1M context
05:58 Context Caching
08:06 Gemini 1.5 Pro in all Google Workspace
08:52 Gemini Flash

Наука

Опубликовано:

 

28 июн 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 14   
@PseudoProphet
@PseudoProphet Месяц назад
Context cashing seems like awesome idea, hundred of usecases.
@samwitteveenai
@samwitteveenai Месяц назад
Totally agree!!
@FredPauling
@FredPauling Месяц назад
Thanks for looking behind the hype on this. 2M token context will fit some big code bases
@kenchang3456
@kenchang3456 Месяц назад
Thanks Sam, looking forward to your review of Gemini Agents and what you think is different about them. Just goes to show you, even very big entities can move quickly when properly motivated.
@ringpolitiet
@ringpolitiet Месяц назад
Thank you for the video, always insightful. I do believe it's "cashing" though, with "cash" pronounced like the paper or polymer banknotes.
@micbab-vg2mu
@micbab-vg2mu Месяц назад
It is good to have options - )
@ConorDean
@ConorDean Месяц назад
Aside from the expense of context caching, does this in someway obsolete a RAG implementation?
@samwitteveenai
@samwitteveenai Месяц назад
Not entirely lots of there are many situations where RAG will still make more sense, but it can be RAG with a big context window.
@SonGoku-pc7jl
@SonGoku-pc7jl Месяц назад
in playground of aistudio or vertex don't pay no? only using api? thanks
@samwitteveenai
@samwitteveenai Месяц назад
yeah just make sure you don't have an API key selected that goes to a project in GCP
@ondrazposukie
@ondrazposukie Месяц назад
Flash is awesome, it's almost as good as GPT-4 models but almost for free
@MudroZvon
@MudroZvon Месяц назад
WTF is "Gemini Era"? 'Era' my butt. What a shitty marketing ploy.
@ShawnThuris
@ShawnThuris Месяц назад
I think it's Google trying to sound trendy but using slang incorrectly
Далее
Mistral's new 7B Model with Native Function Calling
12:23
Gemma 2 - Google's New 9B and 27B Open Weights Models
14:30
I Built a SECRET McDonald’s In My Room!
36:00
Просмотров 9 млн
Google Expands AI Search to All Users
10:28
Просмотров 24 тыс.
Google I/O for Devs - TPUs, Gemma & GenKit
11:01
Просмотров 2,8 тыс.
GPT-4o: What They Didn't Say!
14:14
Просмотров 31 тыс.
Google Gemini vs. ChatGPT
5:13
Просмотров 201
Google Introduces Gemini 1.5 Pro
6:58
Просмотров 76 тыс.
De-Google Your Life - Part 1: Start With Chrome
19:31
Advanced Colab - How to go Beyond the Basics
13:36
Просмотров 4 тыс.
Телефон в воде 🤯
0:28
Просмотров 1,2 млн