GENERATIVE AI

→ View original post on X — @oriolvinyalsml

Deep Think releases with safety expert review before wider deployment

By

@oriolvinyalsml

–

22 May 2025 3h18

Because we're defining the frontier with Deep Think, we're taking extra care. This includes first getting input from safety experts and trusted testers via the Gemini API to gather crucial feedback before wider release.

Veo 3 vs Wan 2.1: Physics Performance on Complex Video Prompts

By

–

22 May 2025 1h19

Tried this prompt with Veo 3:

> televised footage of a cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins, there is commentary (not slow motion)

Wan 2.1 still has the best physics for out-of-distribution prompts. https://t.co/SFuzWufSTW pic.twitter.com/S2F1HvtO0h
— fofr (@fofrAI) 21 mai 2025

Tried this prompt with Veo 3: > televised footage of a cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins, there is commentary (not slow motion) Wan 2.1 still has the best physics for out-of-distribution prompts.

Imagen-4 Generates Cat Typography Art from Clever Prompt

By

–

22 May 2025 1h09

Same prompt, Imagen-4 > the word “cat” where the shapes of all the letters combine to form a cat using only clever typography

Imagen-4 Long Prompts Generate Superior Comic Illustration Outputs

By

–

22 May 2025 0h57

I haven't played with Imagen-4 a lot yet, but it seems like long prompts give the best outputs. Here's a Reve prompt on Imagen-4: > A comic book illustration features a character with spiky hair and intense glowing eyes, wearing torn punk-inspired clothing adorned with chains

→ View original post on X — @replit

Grok 3 Live Search Now Available on Replit Platform

By

@replit

–

22 May 2025 0h55

Get started with Grok 3's Live Search on Replit in just a few minutes https://t.co/tzVgJ0FmlK
— Replit ⠕ (@Replit) 21 mai 2025

Get started with Grok 3's Live Search on Replit in just a few minutes

→ View original post on X — @cursor_ai

Tab Model: 1M Context Windows and Background Agent Preview

By

@cursor_ai

–

22 May 2025 0h50

New Tab model, 1M+ context windows, and a preview of our background agent pic.twitter.com/xEhu05z68n
— Cursor (@cursor_ai) 21 mai 2025

New Tab model, 1M+ context windows, and a preview of our background agent

Veo 3 Creates Perfectly Looping Video with Music and Voice

By

–

22 May 2025 0h29

Veo 3 managed to make a perfectly looping video for this one, music, voice and all.

> a neon splash animation shows "Coming soon on Replicate" and then "Veo 3" against a pink and gold background, funky music, there are people dancing, it's the 80s

We're working on it 🚀 pic.twitter.com/Ub3l9BLMnJ
— fofr (@fofrAI) 21 mai 2025

Veo 3 managed to make a perfectly looping video for this one, music, voice and all. > a neon splash animation shows "Coming soon on Replicate" and then "Veo 3" against a pink and gold background, funky music, there are people dancing, it's the 80s We're working on it