Jinxit

@jinxit79

88 Following

34 Followers

Jinxit pfp

https://uncut.network/user/4296121048/feed/post/60129817123?referrer=5dde4891-9c61-11ef-a15e-42004e494300

0 reply

0 recast

0 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Chronist pfp

My submission to the Higher Digital Art Contest: "Superstellar" is an ode to the deep and meaningful conversations and how they can take us higher together. If you like it, you can mint it now on Zora :) https://zora.co/collect/base:0x0bee1d4c4af91465a5df9efb29759c2c12ba1063/2

4 replies

2 recasts

5 reactions

Jinxit pfp

0 reply

0 recast

0 reaction

Uncut Network pfp

🌟 Welcome to all the followers of Uncut Network! 🌟 Step into a new era where art and blockchain come together! Uncut Network is a thriving community for artists and collectors exploring the Web3 space. From unique digital artworks to vibrant connections, this is where creativity meets decentralization. 🎨✨ Join us and discover the future of digital art! 🔗 http://uncut.network/ #ArtOnChain #Web3Art #Uncut

0 reply

0 recast

0 reaction

Uncut Network pfp

🚀 Exciting news! Uncut’s digital collectibles are going social on WAX, merging art and interaction like never before. Each collectible is now more than just a digital asset; it’s a conversation starter! Dive into showcasing, trading, and sharing unique digital art pieces in Warpcast. #UncutArt #DigitalCollectibles #WAX https://medium.com/wax-io/uncut-wax-digital-collectibles-go-social-d81cb6f72165

0 reply

0 recast

0 reaction

Uncut Network pfp

🚀 Exploring an epic lineup of 168,660+ #WAX and #UNC collectibles on @UncutNetwork! So much unique digital art for collectors to discover. Check it out and join the #NFTCommunity trend! 🔥 #Web3 #DigitalCollectibles https://uncut.network

0 reply

0 recast

0 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Jinxit pfp

Good evening😊

0 reply

0 recast

0 reaction

Jinxit pfp

Good Morning🦊

0 reply

0 recast

0 reaction

𝚐𝔪𝟾𝚡𝚡𝟾 pfp

𝚐𝔪𝟾𝚡𝚡𝟾

The π₀ release introduces a VLA generalist model for dexterous tasks like laundry folding and table bussing. π₀ uses a transformer with flow matching, combining VLM pre-training benefits and continuous action chunks at 50Hz, and is pre-trained on a broad dataset. With distinct pre-training and post-training stages, it supports zero-shot and fine-tuned task adaptation, demonstrating robustness to external interventions, as seen in an uncut video of π₀ folding laundry with a single model. π₀ and its smaller, non-VLM version are evaluated against: - Octo and OpenVLA for zero-shot VLA tasks - ACT and Diffusion Policy for single tasks π₀ surpasses in zero-shot accuracy, fine-tuning for new tasks, and language-following. Compute-parity ablations highlight trade-offs between VLA backbone gains and pre-training costs. Hierarchical methods like RT-H aid complex tasks needing low-level control and high-level planning, though Pi_0’s robust architecture largely drives its performance. (link below)

2 replies

2 recasts

45 reactions

Claus Wilke pfp

AI is not a replacement for competent software developers. Listen to this (excellent) interview with the Cursor team. If somebody knows about AI-generated code it's them. It's obvious there is a huge opportunity for AI-assisted coding, but emphasis is on "assisted." The AI still needs a lot of hand-holding and human supervision. https://www.youtube.com/watch?v=oFfVt3S51T4

1 reply

1 recast

15 reactions

Jinxit pfp

1 reply

0 recast

1 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Jinxit pfp

0 reply

0 recast

0 reaction

Jinxit pfp

Good evening😊

0 reply

0 recast

0 reaction

Chronist pfp

It's very good, one thing I learned is that people don't see as many details as we do ahahahha

0 reply

0 recast

0 reaction

Chronist pfp

Nice colors!!! Love it 😍

0 reply

0 recast

0 reaction