Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Auto rigging without manual weight painting or skeleton construction. Creators/game devs are going to love this. SkinTokens converts skinning to discrete token sequences. uses Qwen3-0.6B for precise skeleton and weight gen across any 3D asset.

Wildminder

11,198 subscribers

17,331 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Nvidia Kimodo Soma 1.1 AI text to Animation is now integrated into my Sorceress 3D character studio for AI 3D models, Daz3D models (or any uploaded model) instant rigging and weight painting & full three.JS / unreal / unity export pipeline with animation blendspace testing for walk cycles. Getting there! Much more to come (link in comments) #aigamedev #gamedev #3DAI #meshy #kimodo #daz3d

Nvidia Kimodo Soma 1.1 AI text to Animation is now integrated into my Sorceress 3D character studio for AI 3D models, Daz3D models (or any uploaded model) instant rigging and weight painting & full three.JS / unreal / unity export pipeline with animation blendspace testing for walk cycles. Getting there! Much more to come (link in comments) #aigamedev #gamedev #3DAI #meshy #kimodo #daz3d

DevDude

12,607 views • 3 months ago

📢 A Sneak Peek: Auto-Rigging on NeuralAI! Get ready to be amazed! Our fearless bald developer just dropped a sneak peek of the next NeuralAI model, but that's not all! We're also testing a groundbreaking new feature: auto-rigging! What's auto-rigging? It's like adding a skeleton to your 3D model, allowing for animation. Currently, rigging is a time-consuming task for many game developers. Imagine the possibilities if it could be done automatically! This potential feature could significantly streamline the 3D creation process, saving animators valuable time and resources. This sneak peek offers a glimpse into the future of NeuralAI. Our commitment to innovation extends beyond creating stunning 3D assets – we're striving to streamline the entire 3D creation workflow. Stay tuned for further updates!

📢 A Sneak Peek: Auto-Rigging on NeuralAI! Get ready to be amazed! Our fearless bald developer just dropped a sneak peek of the next NeuralAI model, but that's not all! We're also testing a groundbreaking new feature: auto-rigging! What's auto-rigging? It's like adding a skeleton to your 3D model, allowing for animation. Currently, rigging is a time-consuming task for many game developers. Imagine the possibilities if it could be done automatically! This potential feature could significantly streamline the 3D creation process, saving animators valuable time and resources. This sneak peek offers a glimpse into the future of NeuralAI. Our commitment to innovation extends beyond creating stunning 3D assets – we're striving to streamline the entire 3D creation workflow. Stay tuned for further updates!

NeuralAI

45,170 views • 2 years ago

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

Amira Zairi

18,116 views • 5 months ago

From generated reference images to riding a robot raptor in Fortnite 🦖 For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting. Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles. Again with the awesome retargeting tools in Unreal Engine / UEFN. I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects. Also curious if there are any upcoming weight painting tools 😄

From generated reference images to riding a robot raptor in Fortnite 🦖 For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting. Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles. Again with the awesome retargeting tools in Unreal Engine / UEFN. I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects. Also curious if there are any upcoming weight painting tools 😄

Jerome | InsaneUnreal

41,297 views • 8 months ago

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 views • 5 months ago

Exclusive (targeted) Red Packets have arrived🧧 Now anyone can target any user segment they like + send out tokens or NFTs to potentially unlimited addresses all at once WITHOUT HAVING TO PAY THE TRANSFER COST🤯 This changes the airdrop game for creators + projects more..👇 On any blockchain today, airdrops to many addresses would cost a small fortune in fees to creators. Not anymore. Not only can you airdrop your NFTs or tokens for only the cost to create the Red Packet (under $0.05) - you can also pick and target whichever user segments you'd like🔥 Airdrop a new NFT or token to previous NFT/token hodlers or even to users who have completed certain actions that you want to reward! Targeted red packets also come with built in spam protection - airdrops only touch a users wallet if they are claimed by the user Creators and project owners can also become whitelisted to receive verified push notifications to users when they receive an airdrop as well as higher sending limits💙 Download the Loopring Smart Wallet today to try them out👇 📱 Or access the Red Packet portal on the Loopring Pro DApp to connect any wallet and start sending👇 💻

Exclusive (targeted) Red Packets have arrived🧧 Now anyone can target any user segment they like + send out tokens or NFTs to potentially unlimited addresses all at once WITHOUT HAVING TO PAY THE TRANSFER COST🤯 This changes the airdrop game for creators + projects more..👇 On any blockchain today, airdrops to many addresses would cost a small fortune in fees to creators. Not anymore. Not only can you airdrop your NFTs or tokens for only the cost to create the Red Packet (under $0.05) - you can also pick and target whichever user segments you'd like🔥 Airdrop a new NFT or token to previous NFT/token hodlers or even to users who have completed certain actions that you want to reward! Targeted red packets also come with built in spam protection - airdrops only touch a users wallet if they are claimed by the user Creators and project owners can also become whitelisted to receive verified push notifications to users when they receive an airdrop as well as higher sending limits💙 Download the Loopring Smart Wallet today to try them out👇 📱 Or access the Red Packet portal on the Loopring Pro DApp to connect any wallet and start sending👇 💻

Loopring💙

31,017 views • 2 years ago

In December, we launched Gemini 1.0 Pro. Today, we're introducing Gemini 1.5 Pro! 🚀 This next-gen model uses a Mixture-of-Experts (MoE) approach for more efficient training & higher-quality responses. Gemini 1.5 Pro, our mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window! The 1M tokens feature unlocks huge possibilities for devs - upload hundreds of pages of text, entire code repos, and long videos and let Gemini reason across them. It's still experimental and early and we’d love your feedback - learn more here.

In December, we launched Gemini 1.0 Pro. Today, we're introducing Gemini 1.5 Pro! 🚀 This next-gen model uses a Mixture-of-Experts (MoE) approach for more efficient training & higher-quality responses. Gemini 1.5 Pro, our mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window! The 1M tokens feature unlocks huge possibilities for devs - upload hundreds of pages of text, entire code repos, and long videos and let Gemini reason across them. It's still experimental and early and we’d love your feedback - learn more here.

Sundar Pichai

853,028 views • 2 years ago

2026 is the year of the splat! This is a single patch of moss - scanned top and bottom - turned into a fully modular 3D asset. Flip it one way and it’s lush moss. Flip it the other and it’s damp, detailed soil. Both sides are real. No fake backsides. No tiling tricks. Ultra-lightweight. Fully real-time. Clones cleanly across geometry. And here’s the key difference - splats don’t really care about intersections. Coplanar overlaps don’t break the asset, they add density and realism. To match this traditionally with 3D you’d need thousands of moss scatters or extremely dense geo - and it would still feel off. One splat patch scales into massive 3D plates with almost no resource cost. This is asset development going forward - modular, DCC-agnostic, and built for modern pipelines. Download the moss scan for free on Gumroad and give it some 3D love. Rendered with OTOY Octane 2026

2026 is the year of the splat! This is a single patch of moss - scanned top and bottom - turned into a fully modular 3D asset. Flip it one way and it’s lush moss. Flip it the other and it’s damp, detailed soil. Both sides are real. No fake backsides. No tiling tricks. Ultra-lightweight. Fully real-time. Clones cleanly across geometry. And here’s the key difference - splats don’t really care about intersections. Coplanar overlaps don’t break the asset, they add density and realism. To match this traditionally with 3D you’d need thousands of moss scatters or extremely dense geo - and it would still feel off. One splat patch scales into massive 3D plates with almost no resource cost. This is asset development going forward - modular, DCC-agnostic, and built for modern pipelines. Download the moss scan for free on Gumroad and give it some 3D love. Rendered with OTOY Octane 2026

Spenser Dickerson

12,242 views • 9 months ago

It’s INSANE how easy it is to Create Photorealistic Characters and Animate them within Minutes using Unreal Engine. Ideation to Render now takes a few hours ONLY and that’s super liberating for artists who want to tell stories 🤯 With Unreal you can now create facial animations for your Metahuman just by using audio without any complex setups, or you can even use your Iphone and Webcam to drive the face animations. It uses AI to predict facial muscle movements, and the results are honestly insane. This is a total game-changer, especially for filmmakers, storytellers and even game developers.

It’s INSANE how easy it is to Create Photorealistic Characters and Animate them within Minutes using Unreal Engine. Ideation to Render now takes a few hours ONLY and that’s super liberating for artists who want to tell stories 🤯 With Unreal you can now create facial animations for your Metahuman just by using audio without any complex setups, or you can even use your Iphone and Webcam to drive the face animations. It uses AI to predict facial muscle movements, and the results are honestly insane. This is a total game-changer, especially for filmmakers, storytellers and even game developers.

Bad Decisions Studio

15,201 views • 1 year ago

GDN: The $KNDX Solution No more hardware bottlenecks Kondux GDN offers streamlined solutions to the problems users may face these days, such as limited access to state-of-the-art hardware & GPU power. We solve this by offloading heavy computational tasks to GDN while streaming 3D assets in real time to any device, regardless of local device capabilities. This means users can easily perform complex activities like high performance gaming, 3D VFX rendering & digital twin simulations for manufacturing without reliance on local GPU power & hardware. For creators, developers & enterprises, this eliminates massive roadblocks for their creative work flow. Instant collaboration through blockchain security In addition, our smart contracts enables sharing digital assets instant and secure, allowing for easy collaboration across multiple platforms. By utilizing our DNA technology, viewing a 3D asset doesn’t automatically grant ownership, and ensures creators 3D assets are protected from unauthorized use. Our kNFT tech brings life, personality & evolution to digital assets. Part of our mission is facilitating the shift of conversation from only traditional static NFTs, towards dynamic high-fidelity 3D assets with real world utility. Advanced interactivity & immersion in real time for all.

GDN: The $KNDX Solution No more hardware bottlenecks Kondux GDN offers streamlined solutions to the problems users may face these days, such as limited access to state-of-the-art hardware & GPU power. We solve this by offloading heavy computational tasks to GDN while streaming 3D assets in real time to any device, regardless of local device capabilities. This means users can easily perform complex activities like high performance gaming, 3D VFX rendering & digital twin simulations for manufacturing without reliance on local GPU power & hardware. For creators, developers & enterprises, this eliminates massive roadblocks for their creative work flow. Instant collaboration through blockchain security In addition, our smart contracts enables sharing digital assets instant and secure, allowing for easy collaboration across multiple platforms. By utilizing our DNA technology, viewing a 3D asset doesn’t automatically grant ownership, and ensures creators 3D assets are protected from unauthorized use. Our kNFT tech brings life, personality & evolution to digital assets. Part of our mission is facilitating the shift of conversation from only traditional static NFTs, towards dynamic high-fidelity 3D assets with real world utility. Advanced interactivity & immersion in real time for all.

Kondux

50,669 views • 1 year ago

OpenAI chairman Bret Taylor talks to about 100 CEOs every month. His answer to the cheap open-weight model panic: cheaper to train does not mean cheaper to use, and the number that decides it is token efficiency. "One thing that I think is a little bit overblown about these open weight models is they're not necessarily cheaper to run. Whether or not they're cheaper to train, you don't care. Because you're using just as many tokens. In fact, they may be less efficient." "There's this thing called token efficiency. And it turns out the frontier models are much, much more token efficient." "A token is to intelligence like a watt is to electricity... how many tokens does it take to complete a task? Not every token is actually equal." "For a lot of tasks, it turns out these frontier models from OpenAI and Anthropic are actually just better than these open weight models... just having open weights isn't actually the main thing driving any of those costs." Later in the same interview he goes after the billing unit itself: "It would be like if you signed up for Gmail and you paid for CPU cycle or something... where the world is going is paying for outcomes." The unresolved column: the chart CNBC airs mid-answer, from Artificial Analysis, prices a completed task at $0.94 on Kimi K3 against $2.75 on Claude Fable 5, efficiency folded in. If that gap holds, the premium he is defending gets earned on quality, not price. - Bret Taylor (Bret Taylor), OpenAI chairman and Sierra co-founder, on CNBC's Squawk Box.

OpenAI chairman Bret Taylor talks to about 100 CEOs every month. His answer to the cheap open-weight model panic: cheaper to train does not mean cheaper to use, and the number that decides it is token efficiency. "One thing that I think is a little bit overblown about these open weight models is they're not necessarily cheaper to run. Whether or not they're cheaper to train, you don't care. Because you're using just as many tokens. In fact, they may be less efficient." "There's this thing called token efficiency. And it turns out the frontier models are much, much more token efficient." "A token is to intelligence like a watt is to electricity... how many tokens does it take to complete a task? Not every token is actually equal." "For a lot of tasks, it turns out these frontier models from OpenAI and Anthropic are actually just better than these open weight models... just having open weights isn't actually the main thing driving any of those costs." Later in the same interview he goes after the billing unit itself: "It would be like if you signed up for Gmail and you paid for CPU cycle or something... where the world is going is paying for outcomes." The unresolved column: the chart CNBC airs mid-answer, from Artificial Analysis, prices a completed task at $0.94 on Kimi K3 against $2.75 on Claude Fable 5, efficiency folded in. If that gap holds, the premium he is defending gets earned on quality, not price. - Bret Taylor (Bret Taylor), OpenAI chairman and Sierra co-founder, on CNBC's Squawk Box.

Karl Mehta

17,336 views • 2 months ago

AI retargeting without manual bone mapping. This could be big for game animation. Different skeletons and body proportions have always made reusing animation a headache. You already have the mocap, but getting it onto a new character can mean another round of bone mapping and cleanup. UMR learns how points on body surfaces correspond, then uses that mapping to transfer motion without manually matching bones. The research focuses on humanoid robots. I see a lot of potential for game animation here. Reusing the same motion library across characters with very different proportions, with less setup for each rig, would make a big difference. I think we'll see people adapting this for 3D workflows pretty soon. For the method and experiments, here's the full paper -

AI retargeting without manual bone mapping. This could be big for game animation. Different skeletons and body proportions have always made reusing animation a headache. You already have the mocap, but getting it onto a new character can mean another round of bone mapping and cleanup. UMR learns how points on body surfaces correspond, then uses that mapping to transfer motion without manually matching bones. The research focuses on humanoid robots. I see a lot of potential for game animation here. Reusing the same motion library across characters with very different proportions, with less setup for each rig, would make a big difference. I think we'll see people adapting this for 3D workflows pretty soon. For the method and experiments, here's the full paper -

Stefan 3D AI

20,983 views • 24 days ago

$my ni-ki, i hope you know that you’ve done nothing wrong! you’re just an incredibly talented artist who puts his heart and soul into his work every single day to bring joy to millions. it’s completely unfair and wrong that people are trying to point fingers at you or direct their anger towards you right now. you’re not responsible for how others behave online, nor are you responsible for the actions of internet bullies who twist reality to spread hate. you cannot carry the weight of an entire online space, nor should you ever have to. it breaks my heart to know that you might see any of this toxicity or feel even a fraction of the weight of things that are completely out of your control. please remember that real engenes will always stand by your side. i love you so much, stay strong. 🤍$

my ni-ki, i hope you know that you’ve done nothing wrong! you’re just an incredibly talented artist who puts his heart and soul into his work every single day to bring joy to millions. it’s completely unfair and wrong that people are trying to point fingers at you or direct their anger towards you right now. you’re not responsible for how others behave online, nor are you responsible for the actions of internet bullies who twist reality to spread hate. you cannot carry the weight of an entire online space, nor should you ever have to. it breaks my heart to know that you might see any of this toxicity or feel even a fraction of the weight of things that are completely out of your control. please remember that real engenes will always stand by your side. i love you so much, stay strong. 🤍

ari, 🪽

848,754 views • 2 months ago

Choplifter (1982) Commodore 64 Originally released by Brøderbund in 1982 and created by Dan Gorlin for the Apple II, Choplifter was later ported to the Commodore 64 by Dane Bigham. This version uses multicolor bitmap mode for smooth parallax scrolling, cleverly extending the horizon into the screen border—no need for sprites for the wide chopper, tanks, or jets. In the game, you pilot a combat helicopter across a vast, side-scrolling desert landscape. Your mission is to blast tanks and dodge fast jets and homing drone missiles with precise forward-facing or rearward shots. Tap the fire button to shoot behind; hold it longer to pivot. Simultaneously, you must manage fuel and execute critical landing sequences. Destroy bunker doors under fire, touch down level to avoid crashing, and then wait as up to 16 frantic hostages sprint aboard. Watching some get gunned down or wander off adds heart-pounding tension. Multiple trips are required to rescue all 64 hostages for a perfect run. You have three lives before mission failure. Your 64 magazine rated it 60%, commenting, "Although not as good as Raid, this game is alright." What would you rate Choplifter?

Choplifter (1982) Commodore 64 Originally released by Brøderbund in 1982 and created by Dan Gorlin for the Apple II, Choplifter was later ported to the Commodore 64 by Dane Bigham. This version uses multicolor bitmap mode for smooth parallax scrolling, cleverly extending the horizon into the screen border—no need for sprites for the wide chopper, tanks, or jets. In the game, you pilot a combat helicopter across a vast, side-scrolling desert landscape. Your mission is to blast tanks and dodge fast jets and homing drone missiles with precise forward-facing or rearward shots. Tap the fire button to shoot behind; hold it longer to pivot. Simultaneously, you must manage fuel and execute critical landing sequences. Destroy bunker doors under fire, touch down level to avoid crashing, and then wait as up to 16 frantic hostages sprint aboard. Watching some get gunned down or wander off adds heart-pounding tension. Multiple trips are required to rescue all 64 hostages for a perfect run. You have three lives before mission failure. Your 64 magazine rated it 60%, commenting, "Although not as good as Raid, this game is alright." What would you rate Choplifter?

Commodore Computer Museum 🕹

14,046 views • 10 months ago

Seriously...GPT 6 can do this now? 😮 Here are the prompts i used: Try out Higgsfield: GPT-6 can now control After Effects directly, designing any motion graphic you want from a simple style reference and building it out layer by layer, all fully editable. Pair it with Higgsfield AI 🧩 to generate the UI graphics and assets you need, then let ChatGPT assemble everything for you. A game changer for motion designers, editors, and creators who want studio-quality graphics without the manual grind. Our mission is to create 100,000 new jobs for creatives, looking to learn and stay ahead in AI? Join GenHQ: #HiggsfieldAI #GPT6 #AfterEffects #MotionGraphics

Seriously...GPT 6 can do this now? 😮 Here are the prompts i used: Try out Higgsfield: GPT-6 can now control After Effects directly, designing any motion graphic you want from a simple style reference and building it out layer by layer, all fully editable. Pair it with Higgsfield AI 🧩 to generate the UI graphics and assets you need, then let ChatGPT assemble everything for you. A game changer for motion designers, editors, and creators who want studio-quality graphics without the manual grind. Our mission is to create 100,000 new jobs for creatives, looking to learn and stay ahead in AI? Join GenHQ: #HiggsfieldAI #GPT6 #AfterEffects #MotionGraphics

Rourke Heath

21,386 views • 26 days ago

2.2+ ROAS ads are starting to look exactly like this not ugc creators, not influencers, and not doctors explaining things on camera just simple animated visuals that clearly show a problem and hint at the solution clean character design, strong curiosity hook, and a message anyone can understand instantly it feels easy to watch and doesn’t trigger that “this is an ad” reaction and that’s exactly why it converts so well no friction, no overthinking, just a visual that makes the problem obvious in seconds these animations are now being used across almost every niche weight loss, gut health, skincare, supplements, and more same visual style, different product behind it, and endless variations to test one concept can be turned into dozens of ads and scaled quickly rt + comment “animated” and I’ll send the setup (follow for dm)

2.2+ ROAS ads are starting to look exactly like this not ugc creators, not influencers, and not doctors explaining things on camera just simple animated visuals that clearly show a problem and hint at the solution clean character design, strong curiosity hook, and a message anyone can understand instantly it feels easy to watch and doesn’t trigger that “this is an ad” reaction and that’s exactly why it converts so well no friction, no overthinking, just a visual that makes the problem obvious in seconds these animations are now being used across almost every niche weight loss, gut health, skincare, supplements, and more same visual style, different product behind it, and endless variations to test one concept can be turned into dozens of ads and scaled quickly rt + comment “animated” and I’ll send the setup (follow for dm)

David

63,514 views • 6 months ago

Today, we’re sharing the first look at TollyLabs’ Uniswap v4 integration: infrastructure designed to bring every way to launch into one fully composable system on Arc. For too long, token launchpads have forced every project through the same rigid templates. Uniswap v4 hooks allow custom logic to operate throughout a market’s lifecycle, from initialization and swaps to liquidity changes and fee handling. For Tolly, that means launches can be designed around the asset, rather than forcing the asset to fit the launchpad. We’re building toward a spectrum of possibilities: • Plain tokens with a standard pad launch. • Creator-tax tokens with configurable buy and sell taxes, with proceeds directed to a wallet, burn, liquidity or another defined allocation. • Reflection tokens that automatically distribute USDC to holders pro rata, without manual claims or external keepers. • Programmable asset pairs that can trade against stablecoins, crypto assets and tokenized stocks, currencies and commodities. • Any combination of these mechanics. Most importantly, these are not isolated templates. They are composable building blocks. Our goal is a new kind of launchpad where creators can visually assemble sophisticated contracts and market structures without treating every launch as a custom engineering project. Simple when you need it. Fully programmable when you don’t. This is a preview of what we’ve been building. We’ll be explaining each component, and the system connecting them, over the coming days as we finish the work.

Today, we’re sharing the first look at TollyLabs’ Uniswap v4 integration: infrastructure designed to bring every way to launch into one fully composable system on Arc. For too long, token launchpads have forced every project through the same rigid templates. Uniswap v4 hooks allow custom logic to operate throughout a market’s lifecycle, from initialization and swaps to liquidity changes and fee handling. For Tolly, that means launches can be designed around the asset, rather than forcing the asset to fit the launchpad. We’re building toward a spectrum of possibilities: • Plain tokens with a standard pad launch. • Creator-tax tokens with configurable buy and sell taxes, with proceeds directed to a wallet, burn, liquidity or another defined allocation. • Reflection tokens that automatically distribute USDC to holders pro rata, without manual claims or external keepers. • Programmable asset pairs that can trade against stablecoins, crypto assets and tokenized stocks, currencies and commodities. • Any combination of these mechanics. Most importantly, these are not isolated templates. They are composable building blocks. Our goal is a new kind of launchpad where creators can visually assemble sophisticated contracts and market structures without treating every launch as a custom engineering project. Simple when you need it. Fully programmable when you don’t. This is a preview of what we’ve been building. We’ll be explaining each component, and the system connecting them, over the coming days as we finish the work.

Tolly

67,804 views • 21 days ago

learned a lot from this conversation with Simon Mo and Matt Bornstein. biggest takeaways for me: -there are a lot of reasons why we should like open-weight models. a lot of these arguments stop at handwavy things like "what if the labs stop releasing frontier models to the public" or "it's lower cost." but simon's position as lead maintainer of vLLM and CEO of Inferact give him authority to talk about some of the other, more interesting and concrete reasons to pay attention to open-weight models, namely that they allow end-users to calibrate latency / other performance metrics with way more customizability than what any of the frontier closed-source labs offer (and without the fear that your job might be met with a refusal at some random point where you're deep in a 2 hour job) -re: the above point...for this reason, a lot of US companies (inferact included!) choose to use open-weight models over their closed-source alternatives. this also isn't limited to internal workloads / research - on a recent a16z podcast the team at Decagon spoke about how something like 90% of their customer service ai agents run on open-weight models that they've fine-tuned. -we should really appreciate how many companies/teams came out researchers fascinated by the wave of very small open-weight models that were being distilled from e.g. gpt-3.5 and earlier models in 2022/2023 (prior to the release of chatGPT!). these small models motivated the development of pagedattention, which then led to vlmm/inferact (at other layers of the stack with similar origin stories, you can look at teams like openrouter or ollama). in other words, we have open-weight models to thank for a bunch of the orchestration infra we now rely on. i think yet another, indirect, way we can point to open-source/weight infra pushing the frontier forward. anyway, a lot more in this convo, it was a lot of fun!

learned a lot from this conversation with Simon Mo and Matt Bornstein. biggest takeaways for me: -there are a lot of reasons why we should like open-weight models. a lot of these arguments stop at handwavy things like "what if the labs stop releasing frontier models to the public" or "it's lower cost." but simon's position as lead maintainer of vLLM and CEO of Inferact give him authority to talk about some of the other, more interesting and concrete reasons to pay attention to open-weight models, namely that they allow end-users to calibrate latency / other performance metrics with way more customizability than what any of the frontier closed-source labs offer (and without the fear that your job might be met with a refusal at some random point where you're deep in a 2 hour job) -re: the above point...for this reason, a lot of US companies (inferact included!) choose to use open-weight models over their closed-source alternatives. this also isn't limited to internal workloads / research - on a recent a16z podcast the team at Decagon spoke about how something like 90% of their customer service ai agents run on open-weight models that they've fine-tuned. -we should really appreciate how many companies/teams came out researchers fascinated by the wave of very small open-weight models that were being distilled from e.g. gpt-3.5 and earlier models in 2022/2023 (prior to the release of chatGPT!). these small models motivated the development of pagedattention, which then led to vlmm/inferact (at other layers of the stack with similar origin stories, you can look at teams like openrouter or ollama). in other words, we have open-weight models to thank for a bunch of the orchestration infra we now rely on. i think yet another, indirect, way we can point to open-source/weight infra pushing the frontier forward. anyway, a lot more in this convo, it was a lot of fun!

Elena

12,922 views • 2 months ago