Nataniel Ruiz ✓

@natanielruizg · Boston, MA · joined 22 Jan 2011

research @GoogleDeepMind | gemini omni | author of dreambooth | generative model personalization

10 421Followers

1 984Following

9 132Posts total

91KViews on collected posts

Son gönderiler

Nataniel Ruiz ✓@natanielruizg23 Sep

yeah it's rough out there 1K views · 0 likes · 0 reposts · 0 replies Open on X →

Nataniel Ruiz ✓@natanielruizg22 Sep

I'm super bored of LLM-stylized papers/blogs. I think we all are? So I asked Claude to explain its tells: https://t.co/5DzFyLLIcO Let's avoid these! I'd much rather read *your* words, see *your* rickety figures, than face down yet another of Claude's anodized corporate veneers. 40.2K views · 559 likes · 36 reposts · 27 replies Open on X →

Nataniel Ruiz ✓@natanielruizg21 Sep

people have to stop underestimating the capabilities and potential of the current paradigm of training models 1.6K views · 12 likes · 0 reposts · 1 replies Open on X →

Nataniel Ruiz ✓@natanielruizg21 Sep

AI comes at you fast https://t.co/igNxc0MIRc 12.9K views · 95 likes · 1 reposts · 5 replies Open on X →

Nataniel Ruiz ✓@natanielruizg16 Sep

a big opportunity to work on one of the coolest models with one of the most dynamics teams on earth. please apply if interested! 2.5K views · 21 likes · 2 reposts · 2 replies Open on X →

Nataniel Ruiz ✓@natanielruizg15 Sep

it’s intriguing. if this line of research works id expect an llm to be calling this type of model frequently 3.4K views · 22 likes · 0 reposts · 4 replies Open on X →

Nataniel Ruiz ✓@natanielruizg14 Sep

We are hiring research engineers and scientists for the Gemini Omni team in London and Zurich. If you are excited about pushing the frontier of generative media, join us! https://t.co/EUfGG6O0EZ https://t.co/Bt0m0bbaSE 11.1K views · 106 likes · 11 reposts · 3 replies Open on X →

Nataniel Ruiz ✓@natanielruizg5 Sep

Super proud of what we’ve achieved with video references on Gemini Omni. If you have the chance take them for a spin. They definitely don’t disappoint and they’re very fun and flexible. Any-to-any is the future of generative models 💫 5K views · 37 likes · 0 reposts · 3 replies Open on X →

Nataniel Ruiz ✓@natanielruizg4 Sep

I've been quite impressed with how flexible video references can be with Omni 1.1. Here's the Luce as a boat, it remains pretty faithful to the reference, while changing the bits it needs to. > [# References <VIDEO_REF_0>video_0.mp4] A boat version of this car https://t.co/Phx6

0:10

13.1K views · 101 likes · 3 reposts · 2 replies Open on X →

Aynı büyüklükteki hesaplara karşı

Son 90 güne ait 9 gönderi, 10K–100K takipçi aralığıyla yan yana. geniş kitleye gösteriliyor, ama izleyenlerin azı tepki veriyor.

Medyan görüntülenme5 044bu hesap92410K–100K için medyan

Erişim, %48.40%bu hesap3.62%10K–100K için medyan

Etkileşim, %0.83%bu hesap1.52%10K–100K için medyan

Ölçüt	Bu hesap	10K–100K için medyan	Oran
Gönderi başına medyan görüntülenme	5 044	924	5.46×
Erişim (görüntülenme ÷ takipçi)	48.40%	3.62%	13.4×
Etkileşim oranı	0.83%	1.52%	0.55×

Bu aralıktaki diğer hesaplar → Başka bir hesapla karşılaştır → Bu kıyas değerleri nasıl kuruluyor →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

13.1K4 Sep

5K5 Sep

11.1K14 Sep

3.4K15 Sep

2.5K16 Sep

12.9K21 Sep

1.6K

40.2K22 Sep

1K23 Sep

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.83%4 Sep

0.79%5 Sep

1.10%14 Sep

0.76%15 Sep

0.98%16 Sep

0.80%21 Sep

0.84%

1.56%22 Sep

0.00%23 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes66.0%953 in total

Reposts3.7%53 in total

Replies3.3%47 in total

Quotes0.9%13 in total

Bookmarks26.1%377 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.