Your curated collection of saved posts and media
Tirunelveli, weβre coming to you! Register Now: https://t.co/SSZfwtbR3D #ChrysalisAI #CorrectionsToConnections #SoulfulAI#AIinEducation #AI #AIinEducation #AIforschools #aiinschools #Tirunelveli https://t.co/XBRZ9XMtSg
Bitcoinβs trustlessness doesnβt pause at sunset β and neither does Native. As the network rests, the proofs keep validating, the system stays sovereign, and BTC remains exactly where it belongs: under your control. See you in the morning. πβ‘ #goNative #BTCFi #CryptoInfrastructure #beeartist
@crycrystallss @Shilllin I had an awesome time taking your Christmas photos together. Cheers β¨ https://t.co/Th9zGyWXzD
GN CT πβ‘ Ledgers donβt fail loudly. They fail when no one is watching. Native exists for that quiet moment. Not to rewrite Bitcoinβs ledger β but to stand guard over it, ensuring every action respects what the ledger already proves. While the hive sleeps, rules remain enforced, history remains intact, and execution never outruns truth. Thatβs guardianship β not control. Good night, CT. ππ @goNativeCC @Tommy_The_Gods #Native #goNative #BTCFi #nBTC #CryptoInfrastructure #beeartist
quick hack iβve been using to catch narrative pivots: search TL with min_faves:10 -filter:replies -filter:nativeretweets around tickers/themes, then bump to min_replies:1 to see convo depth. add from:yourID to audit which of your posts actually moved @NetworkNoya turns that raw scan into signal. it reads microβpatterns in sentiment and narrative flow, flags when interest consolidates or when doubt starts to creep, and maps where momentum is forming before charts react my play: surface early posts, let $NOYAβs read guide size/entries, and stake for loyalty while automations execute across chains #AttentionFi #Web3 who else is running this workflow?
Secure your coding agents with virtual filesystems and better document understanding. Building safe AI coding agents requires solving two critical challenges: filesystem access control and handling unstructured documents. We've created a solution using AgentFS, LlamaParse, and @claudeai. π‘οΈ Virtual filesystem isolation: agents work with copies, not your real files, preventing accidental deletions while maintaining full functionality π Enhanced document processing: LlamaParse converts PDFs, Word docs, and presentations into high-quality text that agents can actually understand β‘ Workflow orchestration: LlamaIndex Workflows provide stepwise execution with human-in-the-loop controls and resumable sessions π§ Custom tool integration: replace built-in filesystem tools with secure MCP server alternatives that enforce safety boundaries This approach uses AgentFS (by @tursodatabase) as a SQLite-based virtual filesystem, our LlamaParse for state-of-the-art document extraction, and Claude for the coding interface - all orchestrated through LlamaIndex Agent Workflows. Read the full technical deep-dive with implementation details: https://t.co/IiCW8Bo0NZ Find the code on GitHub: https://t.co/mekxD21O4E
πΊοΈTowards A Roadmap of Video World ModelπΊοΈ We conceptualize the progression of video generation through **four generations**, in which the core capabilities ultimately culminating in a world model. π‘ https://t.co/Cr9T4Uq7QP π https://t.co/NvXmw6JbbG π§βπ» https://t.co/lv4QuAW08m https://t.co/VYYR8Yk239
π Announcing Echo β our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world β not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly β even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering β but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows β digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations β all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction β environments that donβt just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. π #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out: https://t.co/QgsuLdhoe6
post here: https://t.co/7BDznUr9VM
Meta presents Exploring MLLM-Diffusion Information Transfer with MetaCanvas https://t.co/GnBqAingOh
discuss: https://t.co/VuMoPg6XXU
Resemble AI released chatterbox-turbo on Hugging Face https://t.co/qGwUyM6QXt
app: https://t.co/wT3MHAFIKU
model: https://t.co/qYDMapLrVr
β¨ Meet our new open family of models: @NVIDIA Nemotron 3 Open in weights, data, tools, and training, Nemotron 3 is built for multi-agent apps and features: β’ An efficient hybrid MambaβTransformer MoE architecture β’ 1M token context for long-term memory and improved reasoning β’ Multiβenvironment reinforcement learning via NeMo Gym for advanced skill adaptation Plus NVFP4 pre-training, latent MoE, 1T tokens of data, and more. πRead the details in our tech blog: https://t.co/9FD1jGp3zc π€ Try the model on @huggingface: https://t.co/n7an9b7hN9
NEWS: NVIDIA announces the NVIDIA Nemotron 3 family of open models, data, and libraries, offering a transparent and efficient foundation for building specialized agentic AI across industries. Nemotron 3 features a hybrid mixture-of-experts (MoE) architecture and new open Nemotron pretraining and post-training datasets, paired with NeMo Gym, an open-source reinforcement learning library that enables scalable, verifiable agent training. Read more: https://t.co/ldf247t3Zz
IBM dropped CUGA, open-source enterprise agent to automate boring tasks π₯ > given workspace files, it writes and executes code to accomplish any task π€― > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM π here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail π€― they release code, a blog and a demo ππ» you can run this locally
had some time tonight and hacked on my first environment to get models to reverse chinese text with @PrimeIntellect's environments and @willccbb's verifiers library. This was surprisingly easy to get started! Next step training a small model~ https://t.co/eexuycGlTI
Nano Banana Proηζ β γγγΉγζ½εΊ β η·¨ι Now you can do it on Manus https://t.co/XxfG0gjwhx
Nano Banana Proηζ β γγγΉγζ½εΊ β η·¨ι Now you can do it on Manus https://t.co/XxfG0gjwhx
Grok Code is the only model with insanely high trillionβtokenβscale usage on Kilo Code β nearly 5Γ more than the next most-used model It has consistently ranked #1 ever since it first took the top spot https://t.co/sO9E5dAxeV
π#GateWeb3Wallet has supported the #Injective Non-EVM type networkοΌ π₯@injective is an interoperable #Layer1 blockchain powering next-generation #DeFi applications πStay tuned for further updates! πEnter Web3πͺοΌhttps://t.co/kaEf8OhzAx #GateWeb3 #Injective #Newchain https://t.co/DFoN1fJ7oj
This map will save mapping btw this is legitimate art to me and i will not elaborate its just beautiful https://t.co/w6EMvBC4LG
The Western Hemisphere has been Trumpified. π΅ Right Wing Governments: 12 π΄ Left Wing Governments: 8 After the socialist regime in Venezuela falls soon, Cuba is next. https://t.co/UuBMRmAPel
This is happening mad fast! I started to realize this when moving all my workflows to Claude Code Skills. Painful at first, but then suddenly moving at speeds never imaginable. I hear more companies embracing skills, which accelerate things more. Good read! https://t.co/HsgySimauW
How can we make a better TerminalBench agent? Today, we are announcing the OpenThoughts-Agent project. OpenThoughts-Agent v1 is the first TerminalBench agent trained on fully open curated SFT and RL environments. OpenThinker-Agent-v1 is the strongest model of its size on TerminalBench, and sets a new bar on our newly released OpenThoughts-TB-Dev benchmark. (1/n)
All the frontier AIs now pass all levels of the very challenging Chartered Financial Analyst (CFA) exam The paper used paywalled, new mock exams to reduce the risk of leakage but AI grading for the essays. Interestingly, prompting strategy doesn't matter for most question types https://t.co/k5PsKGObi7
Apple just released Sharp Sharp Monocular View Synthesis in Less Than a Second https://t.co/bXoFtIPmWs
EgoX Egocentric Video Generation from a Single Exocentric Video https://t.co/t2RWPiqSPR
discuss: https://t.co/XnYeSzpn2Y
SVG-T2I Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder https://t.co/cN3g4qn6Js
discuss: https://t.co/NmUO0sare6
