Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Massive performance improvement. This is a bit more of technical post, but man do I love this stuff! Units navigate the map using a 'Navigation Mesh'. Before, I was using one giant nav mesh that spanned the entire map. The more objects that were placed (especially on a large...

60,072 Aufrufe • vor 7 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

The architecture of this new world model is one of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.

Santiago

30,189 Aufrufe • vor 1 Monat

🚨 WARNING: MONDAY WILL BE THE WORST DAY OF 2026!! Trump just OFFICIALLY confirmed that the US will invade Cuba IMMEDIATELY after finishing with Iran. Should I remind you what happened to the markets when the US started strikes on Iran? When markets start pricing that reality, this will NOT be just another headline. This is a geopolitical catalyst hitting an already fragile system. Stocks will dump. Crypto will dump. Risk will get hit all at once. This is no longer just about Iran. It is about expansion. And now the pressure just multiplied. Because when one conflict is still burning and the next target is already being named, markets stop pricing de-escalation. They start pricing EXPANSION. And expansion is where the real damage starts. That one fact explains a lot. This is NOT just a Cuba story. This is about the war map getting bigger, not smaller. There are only a few ways this goes from here, and they are NOT equal. - LIGHT SHOCK: it stays at the headline level, markets panic first, then stabilize if nothing follows. - HEAVIER SCENARIO: Cuba starts getting priced as the next pressure point, and regional risk starts spreading. - WORST CASE: markets start pricing a second front after Iran, and the whole risk picture changes again. That last one is the REAL danger. Because if Iran was phase one, Cuba becomes phase two. Now connect the dots. This does NOT stay political. It hits flows. It hits freight. It hits regional risk. It hits every market that was hoping Iran was the end of the story. That is why this matters so much. Because once markets stop pricing closure and start pricing expansion, the whole framework changes. Not a dip. Not a fake panic. A REAL warning that the geopolitical map is getting bigger again. I’ve studied macro for 10 years and I called almost every major market top, including the October BTC ATH. Follow and turn notifications on. I’ll post the warning BEFORE it hits the headlines.

Wimar.X

125,262 Aufrufe • vor 3 Monaten

Jeff Bezos never has to work another day in his life. He works like he needs the job. Ninety five percent of his time goes to AI. Meetings from 9 to 7. Technical papers after. His reason is one sentence. Bezos: “The world is so interesting right now. We’re in multiple golden ages at once.” Not one. Several. Running at the same time. For ten thousand years, humanity got one breakthrough per era. Fire. The wheel. The printing press. Electricity. A single leap. Then centuries of silence. That rhythm just broke. Artificial intelligence. Space. Gene editing. Robotics. Energy. All of it arriving inside the same ten years. Nothing in recorded history looks like this. So why does it feel like an ending instead of a beginning. Because the mind evolved to flinch at danger, not to measure it. Collapse feels loud. Progress feels like it belongs to someone else. Step back far enough and the truth turns almost violent. Every person who came before you lived and died in the world they were born into. Nothing moved. Nothing shifted. The map they were handed was the map they returned. You were dropped into the one decade where the whole thing changes at once. Everyone before you knew only the old world. Everyone after you will know only the new one. You are the only ones who will ever see both. Bezos: “There’s never been a more extraordinary moment to be alive.” That was not optimism. It was arithmetic. You were not born too late. You were born on the seam between two worlds. Almost no one alive will realize they are standing on it.

Dustin

39,307 Aufrufe • vor 1 Monat

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.

Nexlow

84,925 Aufrufe • vor 24 Tagen