내가 좋아할 만한 콘텐츠
terminal-based SSH connection manager with search and edit features
Meta just did the unthinkable. They figured out how to train AI agents without rewards, human demos, or supervision and it actually works better than both. It’s called 'Early Experience', and it quietly kills the two biggest pain points in agent training: → Human…
spec-driven workflow for AI coding assistants, no API keys needed
For those that think this is hype: no it's not. I invented a little training/eval set last night. Model score is about 50% with my own optimized prompt. GEPA takes that to 70% with auto="light" optimization. I imagine this can go to 90% with heavy optimization. Insane…
One of the awesome features of the SuperSplat Editor is that it can render high quality videos of your 3D Gaussian Splats. #PlayCanvas #OpenSource
Spatial representations are central to world models🌍 SuperDec is an extremely compact 3D scene representation (replacing millions of Gaussians with just a few hundred primitives) ideal for abstract reasoning and planning in 3D ➡️super-dec.github.io ✨Oral @ICCVConference
Are photorealistic representations all we need? In SuperDec, we turn millions of points into compact and modular abstractions made of just a few superquadrics!🧩 Try our code and get a compact representation of your favorite scene!🚀 👾: github.com/elisabettafede…
BREAKING: OpenAI to partner with OpenAI to help fund OpenAI. OpenAI up 90%.
🎨 GOLDEN AGE GRIT 🎨 Prompt : [SUBJECT] depicted in the Golden Age Grit style, with a grainy texture, simple lines, and a limited color palette. Focus on dynamic action and dramatic poses using [COLOR1] and [COLOR2] as primary colors. Check ALTS
![LudovicCreator's tweet image. 🎨 GOLDEN AGE GRIT 🎨
Prompt :
[SUBJECT] depicted in the Golden Age Grit style, with a grainy texture, simple lines, and a limited color palette. Focus on dynamic action and dramatic poses using [COLOR1] and [COLOR2] as primary colors.
Check ALTS](https://pbs.twimg.com/media/G3MwNnUWoAAzeae.jpg)
![LudovicCreator's tweet image. 🎨 GOLDEN AGE GRIT 🎨
Prompt :
[SUBJECT] depicted in the Golden Age Grit style, with a grainy texture, simple lines, and a limited color palette. Focus on dynamic action and dramatic poses using [COLOR1] and [COLOR2] as primary colors.
Check ALTS](https://pbs.twimg.com/media/G3MwN0EWwAAJqcS.jpg)
![LudovicCreator's tweet image. 🎨 GOLDEN AGE GRIT 🎨
Prompt :
[SUBJECT] depicted in the Golden Age Grit style, with a grainy texture, simple lines, and a limited color palette. Focus on dynamic action and dramatic poses using [COLOR1] and [COLOR2] as primary colors.
Check ALTS](https://pbs.twimg.com/media/G3MwOCmXwAAuFJ6.jpg)
![LudovicCreator's tweet image. 🎨 GOLDEN AGE GRIT 🎨
Prompt :
[SUBJECT] depicted in the Golden Age Grit style, with a grainy texture, simple lines, and a limited color palette. Focus on dynamic action and dramatic poses using [COLOR1] and [COLOR2] as primary colors.
Check ALTS](https://pbs.twimg.com/media/G3MwOQkXkAE45Ae.jpg)
> smol chinese ai lab > trained on 200x less data than deepseek v3.2 > 2.1x faster when loading context > 2.3x faster generating tokens > 99% same accuracy they’re speedrunning ai race fr!
🤔Loving the new DeepSeek-V3.2? 🔥Remember the first sparse-native models! ✨ InfLLM‑V2: Seamless Long‑Context Adaptation Paper: arxiv.org/abs/2509.24663 1️⃣ Ultra‑fast adaptation: only 5B long‑text tokens to train sparse attention (vs. ~1T in DSA from DeepSeek-V3.2) 2️⃣…
Happy to finally release v.0.11 of MFLUX with Qwen Image support! uv tool install --upgrade mflux Simply swap `schnell` or `dev` for `qwen`: mflux-generate --model qwen --prompt "..." --steps 20 and the model will begin to download github.com/filipstrand/mf… #MLX #Qwen #GenAI
Lost in stories and splashes. Prompt: { "A highly detailed, surreal digital illustration of a man front-facing, drawn with expressive black line art emphasizing the intricate texture of hair, neck, and shirt. The background features faded, sepia-toned vintage newspaper pages…
🔊 Google’s Gemini 2.5 Native Audio Thinking hits 92% on Big Bench Audio, the leading speech to speech reasoning. 👏 It trades speed for quality at 3.87 s to first audio, while the version without thinking is 0.63 s and fastest overall. Big Bench Audio has 1,000 spoken…
Google’s Gemini 2.5 Native Audio Thinking is the new leading Speech to Speech model per our Artificial Analysis Big Bench Audio benchmark The new model achieves a score of 92% on Big Bench Audio, the highest result recorded by Artificial Analysis to date. This not only places it…
Prompt: A group of friends having lemonade under a big oak tree on a sunny afternoon, laughter captured mid-moment. The table is covered with mismatched cups, and a gentle breeze rustles the leaves. Rendered in colored ink illustration style with light linework, playful details,…
Moondream doesn’t just see the game, it understands it. “Who’s winning?” “Fallen player?” “Player with the ball?” “Main sponsor?”. It spots them all in a single frame. Smart. Fast. Free → moondream.ai.
runs multiple AI agents in parallel, they share updates and refine each other's work until reaching consensus
Try this Oil painting and Watercolor Look Use Gemini ai 🌸 Prompt 👇🏻 A very beautiful and joyful young Asian woman in a dynamic pose, laughing with her black hair blowing in the wind. She is wearing a white jacket over a pink t-shirt and blue cargo pants. Behind her, scraps…
Let your robot peek around corners, size up the gap between chairs, and know exactly where everything sits. 🤖 Our new work SR-3D masters this kind of spatial reasoning. It learns from multiple views to understand distances, layouts, and how objects relate in 3D space.
I made a RL policy that guesses where a picture was taken without GPS data It continuously learns, updating its weights with every use in realtime -- over the weekend it improved 13.9% with <100 images Best of all, it does this without ever storing any image data, link below
made an app that guesses where you are in the world with just a picture using image embeddings trained on street view data first time using swiftui, consumer apps in general, TestFlight below
Visions – a series of procedural data paintings in perpetual flux. 30th October on ⛵️@OpenSea Get ready to misremember.
United States 트렌드
- 1. $CHA 1,148 posts
- 2. #TORQSports N/A
- 3. Nancy 86.5K posts
- 4. Supreme Court 124K posts
- 5. Argentina 452K posts
- 6. Waddle 4,955 posts
- 7. Banish 1,530 posts
- 8. #TWICExVictoriasSecret 31.5K posts
- 9. #PokemonGO 3,852 posts
- 10. Malcolm Brogdon 4,717 posts
- 11. #VSFashionShow 51.2K posts
- 12. SCOTUS 39.3K posts
- 13. TWICE LIGHTS UP VSFS 29.4K posts
- 14. Olave 3,987 posts
- 15. Big Balls 31.3K posts
- 16. #ClockTower1Year 1,067 posts
- 17. Biker Boyz N/A
- 18. Martha 22.8K posts
- 19. Voting Rights Act 41.4K posts
- 20. Meyers 2,909 posts
Something went wrong.
Something went wrong.