Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Min Choi Profile picture
@minchoi
Mar 25 • 9 tweets • 3 min read • Read on X
Scrolly
This is wild.

Google just dropped Gemini 2.5

And it just topped the AI Arena Leaderboard with the biggest jump ever.

Here's what it all means, and 6 wild examples:

1. Interactive health and economic charts
2. Reflection Nebula Simulation
3. Dino Game
4. Cosmic Fish
5. Flying Boids in Hexagon
6. Mandelbrot Set Demo
Major benchmark gains across all categories, including a groundbreaking 18.8% on Humanity's Last Exam. Image
Gemini 2.5 Pro hit #1 AI spot beating Grok-3 & GPT-4.5 by 40pts!
If you enjoyed this thread,

Follow me @minchoi and please Bookmark, Like, Comment & Repost the first Post below to share with your friends:

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Min Choi

Min Choi Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @minchoi

Min Choi Profile picture
Mar 27
I used GPT-4o Image Generation to create photorealistic version of famous artworks.

The results are wild

1. "The Girl with a Pearl Earring" by Johannes Vermeer Image
2. 11. "Mona Lisa" by Leonardo Da Vinci Image
3. "Self Portrait" by Vincent Van Gogh Image
Read 12 tweets
Min Choi Profile picture
Mar 26
ChatGPT GPT-4o Image Generation is breaking the Internet.

People can't believe it's 100% AI, it's insanely good.

10 wild examples:

1. Beachside selfie (prompt in ALT) PROMPT: gorgeous young woman taking a selfie at the beach, skin drenched, blue bikini, looking at camera, lips pursed. aspect ratio 2:3
2. Convert photos into Studio Ghibli anime style
3. One prompt comic
Read 11 tweets
Min Choi Profile picture
Mar 26
GPT-4o just got an INSANE upgrade!

OpenAI just dropped native Image Generation in GPT-4o.

Image & Text quality is insane. 100% AI

10 wild examples (prompts included):

1. Polaroid style photographs PROMPT: Generate a candid, Polaroid-style photograph of four diverse friends in their early 20s at a gritty dive bar. The lighting features a very harsh, direct flash, creating sharp shadows and giving the photo a very overexposed, vintage instant-camera feel. Colors should be slightly muted, evoking nostalgic, early-2000s party vibes. The aesthetic is casually emo. No border or logos or signs. There's an interesting looking wall behind them with some light graffiti. Quality of the image should be very sharp and detailed (very little grain). The energy should be silly and chaotic. They're e...
2. Photorealistic image at a farmer's market circa 2006 PROMPT: Generate a photorealistic image of farmer's market in toronto on a saturday in summer 2006, it's a beautiful late june day, people are shopping and eating sandwiches. in focus should be a young asian girl wearing denim overalls and sipping on a strawberry banana smoothie - rest can be blurred. the photo should be reminiscent of that a digital camera from 2006 would take, with a timestamp like a printed photo would have. aspect ratio should be 3:2
3. Incredible Text generation like street signs

PROMPT:

Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign.

Context:
a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)\n Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic.

Characters:
one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs.

Composition from background to foreground:
streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shotImage
Read 11 tweets
Min Choi Profile picture
Mar 24
ByteDance dropped InfiniteYou

This AI creates infinite realistic versions of YOU, any style, in seconds.

Here's how & where to try it: 👇
2/ First, go to the HuggingFace demo:


✅Upload your photo
✅Select realism & anti-blur
✅Type your style prompt
✅Hit Generate! huggingface.co/spaces/ByteDan…
Model Card
huggingface.co/ByteDance/Infi…
Read 6 tweets
Min Choi Profile picture
Mar 23
Vibe Coding just changed coding forever.

People are building wild apps & games insanely fast with AI. There is a massive shift.

10 examples:
1. Andrej Karpathy vibe coded a whole iOS app in Swift (without prior Swift experience)
2. Game created with Claude + Grok
Read 12 tweets
Min Choi Profile picture
Mar 23
JARVIS-VLA just dropped

This AI can play Minecraft using 1,000+ tasks from human instructions, craft, mine & fight!

Watch it attempt to kill Enderman 👇
JARVIS is an AI trained to follow human commands visually, playing games like Minecraft using keyboard/mouse.

It understands tasks from text instructions and visually interacts with objects, tools, mobs & environments.

JARVIS can learn and master over 1000 skills—like crafting, mining, fighting, and even cooking—without manual coding.

It can reflect on mistakes, rethink strategies, and self-improve actions to achieve tasks efficiently.

JARVIS learns by watching examples (vision-language data) instead of needing detailed step-by-step training.Image
Read more ata HuggingFace Page:
huggingface.co/papers/2503.16…
Read 7 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(