10x speedup: OpenAI's privacy-filter on MLX vs CPU, side... by side in your browser. 1,818 tok/s vs 179 tok/s. Real-time PII redaction across English, German, French. On-device. No cloud. Privacy-first. Which model should we port next?show more

Gemma 4 12B QAT (dense) achieves 1000+ tokens/sec prefill... on 8GB VRAM with 120k context Gemma 4 12B QAT (dense), TurboQuant (Without MTP), RTX 4060 8GB VRAM: Prefill: 1000+ tok/s (42% increase) Decode: 25+ tok/s (25% increase) Context: 120k (150% increase) prefill was 700 tok/sec and decode 20 tok/sec with only 48k context without turbo quant (older test with mtp link in the comments) llama.cpp TurboQuant flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -c 120000 --cache-type-k q8_0 --cache-type-v turbo3 -ngl 99 --port 8080 tested with a 27k prompt, 120k context loaded. -ngl 99 here isn't a typo, full 12B dense, every layer on GPU, on an 8GB card. that's the part worth sitting with. The model has vision, audio input, thinking/reasoning and fits your 8GB card. TurboQuant's KV cache savings are what free up the room to do that at 120k context. side by side with yesterday: 26B A4B MoE got 320+ tok/s prefill. this dense 12B is clearing 1000+ rig: RTX 4060 8GB · i7H · 16GB RAM same two flags as yesterday, different model size: --cache-type-k q8_0 --cache-type-v turbo3 thanks to TheTom/llama-cpp-turboquant, TurboQuant fork of llama.cpp by Tom Turney (Tom Turney) to make this work. unsloth's model quant huggingface and the llama.cpp fork github link in the comments Do you prefer a dense or a MoE for your 8GB card?show more

Holy shit... Microsoft open sourced an inference framework that... runs a 100B parameter LLM on a single CPU. It's called BitNet. And it does what was supposed to be impossible. No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed. Here's how it works: Every other LLM stores weights in 32-bit or 16-bit floats. BitNet uses 1.58 bits. Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for. The result: - 100B model runs on a single CPU at 5-7 tokens/second - 2.37x to 6.17x faster than llama.cpp on x86 - 82% lower energy consumption on x86 CPUs - 1.37x to 5.07x speedup on ARM (your MacBook) - Memory drops by 16-32x vs full-precision models The wildest part: Accuracy barely moves. BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat. What this actually means: - Run AI completely offline. Your data never leaves your machine - Deploy LLMs on phones, IoT devices, edge hardware - No more cloud API bills for inference - AI in regions with no reliable internet The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine. 27.4K GitHub stars. 2.2K forks. Built by Microsoft Research. 100% Open Source. MIT License.show more

Chase Hughes: "Psychopaths are attracted to large cities. In... my analysis, Dr. Robert Hare has done most of the research on psychopaths. In my analysis, I think that cities are not just attracting psychopaths, I think that cities are helping to manufacture them." Drawing from Dr. Robert Hare's landmark research on psychopathy, Hughes argues urban environments—high anonymity, constant stimulation, exploitative opportunities—rewire people toward cold, manipulative traits. It's not just selection; it's creation. In 2026's urban chaos debates (riots in Minneapolis, blue-city breakdowns trending hard), this hits different: Are megacities breeding the very disorders we blame on "bad people"? 14-sec clip exposing the "psychopath factory" theory 👇 Rural life vs. city grind: Which side do you think preserves empathy better? Drop your take—no filter.show more

the 24gb vram tier is enough for most builder... work in 2026. gemma 4 31b dense on my rog scar 18 just autonomously built a production hero section in one prompt, one html file and 5 minutes end to end. hardware: rog scar 18, rtx 5090 laptop 24gb vram. model: google gemma 4 31b dense at q4_k_m quant, using 22.8 of 24gb. engine: llama.cpp built for blackwell (sm_120). harness: hermes agent with native tool parsing. speed: 15 tok/s sustained, 94 watts, 50c. flags i used: ./build/bin/llama-server -m ~/models/gemma4-31b/google_gemma-4-31B-it-Q4_K_M.gguf -ngl 99 -c 131072 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --jinja --host 127.0.0.1 --port 8080 if you own 24gb vram in 2026, you have enough for most ui work, most agentic coding, most autonomous builds. no subscription, no one logging your prompts. a dense open model on consumer hardware shipping real software on your desk. this was the warmup. full page next on same hardware, then the octopus invaders final multifile autonomous challenge.show more

Self Attention vs Cross Attention by hand ✍️ Resize... the matrices yourself 👉 Two attention mechanisms, side by side. Both project X into queries; both compute attention via S = Kᵀ × Q and F = V × A. The only difference is the source of K and V. Self attention uses X for everything. Q, K, and V all come from projecting X. Each X token attends to every other X token. The score matrix S is square — 128 × 128. Cross attention uses X for queries and a second sequence E for keys and values. Each X token attends to every E token instead. The score matrix S is rectangular — 64 × 128. Notice what's shared and what's not: X is the same in both — same 36 × 128 input. Q and K share the 16 dimension — that's what makes the dot product Kᵀ × Q valid in either case. V dimensions are independent: self-attention uses 12, cross-attention uses 12. The choice doesn't depend on which mechanism you're using; it depends on what output dimension your downstream layer expects.show more

Introducing HermesAgent-20, a new Bench Pack for BenchLocal. 20... scenarios extracted straight from the Hermes Agent source code, run against a REAL Hermes instance. The actual workload you'd put your model through. Why I built BenchLocal in the first place: most benchmarks are too abstract. We use local LLMs for practical work, and finding the right model for YOUR task efficiently is the single most important thing, especially when you're constrained to what fits on your machine. BenchLocal is a framework: providers, models, side-by-side comparison, all in one UI. Bench Packs are the unit of testing: ToolCall-15 and BugFind-15 shipped first, and when I launched the BenchLocal 0.1.0, added StructOutput, ReasonMath, InstructFollow, DataExtract. Now, HermesAgent-20 is the newest. Bench Packs install like VS Code extensions. The SDK is open, write your own, share it, grow the ecosystem. Here's the goal: a community-built, practical evaluation layer for the local LLM space. Early numbers on HermesAgent-20: > GLM 5.1 — 85 > Gemma4 31B — 83 > Qwen3.5 27B — 79 > MiniMax M2.7 — 76 Upgrade to the latest BenchLocal to install HermesAgent-20 (SDK update required).show more

you're paying $20/mo for something your $500 GPU can... already do. Gemma 4 26B A4B QAT MoE + Hermes Agent running on a single RTX 4060 (8GB VRAM). Built a vision capable, 100% free, 100% local, private AI assistant that lives in my Chrome browser. No API keys. No cloud. No subscriptions. 100% vibe coded. 0% handholding. It has full context of whatever's on my screen can answer questions, summarize pages, extract data, and see images. Same local model handles everything, no external calls, ever. keep reading for the model and hermes agent tips i learnt while building this locally. Here's the exact setup for anyone running local LLMs on 6-8 GB VRAM: llama.cpp server flags (on my NVIDIA RTX 4060 8gb VRAM): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --cache-type-k q8_0 --cache-type-v q8_0 -c 150000 --port 8080 Throughput with quantization: Prefill: 200-250 tokens/sec Decode: 20-25 tokens/sec reduce context if oom on 6 gb vram card. Key learnings: - Quantize KV cache to q8 for faster prefill/decode. Prefill goes from 100-150 (unquantized) to 200-250 tok/s (q8). - But watch out, once actual context grows past ~50k tokens on high entropy workloads, q8 KV quantization can cause hallucinations. Low entropy workloads are mostly unaffected. If you see it happening, drop the quantization. This is common across all local models. - In Hermes Agent settings -> Memory & Context, bump compression threshold from default 0.5 to 0.7. Default triggers way too frequent context compression and eats time. Up next: add persistent memory, web search, tool calling, streaming output and whatever you suggest. Running a 26B MoE with vision + 150k context window on 8GB VRAM would've sounded impossible 6 months ago. Works the same on the NVIDIA RTX 3060 Ti, 3070, 4060 Ti, 5060, 2080, or any 8GB card. VRAM is the only requirement. Local AI agents are closer than people think. You just need to know where the knobs are. Model's Unsloth quant hugging face link in the comments. Have you tried Hermes agent by Nous Research yet? What are you building with local LLMs? Drop it below, let's see what this community is shipping.show more

here's how the whole thing works. claude code doesn't... care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.show more

Introducing Pods Hyperspace Pods lets a small group of... people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.show more

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech... model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.show more

Proud to announce the in-depth collaboration between Kingnet and... Alibaba Cloud in AI Gaming. Alibaba Cloud provides world-leading cloud computing, big data, and AI services, with disclosed revenue exceeding $15 billion in 2024, which is one of the most renowned global server providers. When two superpowers collide, the game changes. 🌊AI Gaming R&D By integrating Qwen 's LLM and Alibaba Cloud 's PAI platform (including PAI-iTAG, PAI-Designer, PAI-DSW, PAI-DLC, and PAI-EAS), Kingnet has emerged as one of the gaming industry's pioneers in AIGC-powered content generation and AI rendering. Together, we are accelerating the realization of no-code game development. 🌊GPU Computing Resources Alibaba Cloud delivers GPU-accelerated elastic computing services with exceptional processing power, supporting diverse workloads including deep learning, scientific computing, graphics visualization, and video processing - providing robust GPU computing capabilities for KingnetAI's demanding requirements. 🌊Cloud Service Optimization Cloud server deployment has become the mainstream choice for small and mid-sized game studios in global operations. Leveraging Alibaba Cloud server advantages, we will develop and deploy more cloud-native games to meet user demands. The disruptive innovation we're bringing to the industry: 🔸Minute-scale game asset production replaces traditional week/month-long cycles 🔸Single-digit dollar development costs VS traditional four-figure entry thresholds 🔸AI-powered NPCs with behavioral engines deliver dynamic player interactions, breaking static story constraints, etc. 🔜Kingnet AI V2 is approaching launch. The Agent system and game generation engine will be officially deployed across 3 chains: 🔹Leveraging Solana high throughput and low gas fee , Solana has consistently been a developer favorite, latest product will be deployed on Solana - with users paying $SOL for on-demand asset creation fees. 🔹Another key partner is BNB Chain ,We are actively participating in both the #BNBAIHack and the latest MVB 10. Powered by BNB Chain long-standing support for AI innovation. Kingnet V2 and NFT drop will be deployed on BNB Chain, providing developers and the community with comprehensive game-generation tools and support. 🔹As an early strategic partner of Kingnet, TON 💎 @TONEastAsia was one of the earliest chain to connect Web2 and Web3, Kingnet V2 will be deployed on TON, providing TON game developers with low-cost, high-efficiency asset generation, and supporting users to use $TON as an asset generation cost. The Future of AI Gaming is coming.show more

🚀10 days to the biggest #DePIN roundtable on X,... first in dual language, global🌏 event. Top 5 projects for innovation & development, Flux I Decentralized Cloud IoTeX Streamr Network PowerPod DRIFE, 5 amazing speakers, Ting | PowerPod raullen Firdosh | DRIFE @Mark_Streamr, great host & translator Walid Cryptopedia confront each other on an amazing Agenda: - Quick introduction to DePIN - Project presentation - How to get to Mass adoption - Challenges and obstacles - DePIN, Decentralization VS Centralization - Green energy, electric cars, costs, benefits, implementation of decentralized charging systems. - Power of AI in DePIN - Comparing technologies (smartphones, devices, software) - Real Word Assets (RWA) and the future Will #DePIN one day be able to replace or complement centralized networks? Giveaway, $1200. 60 will be the lucky winners $20 each in Token, live now on Zelay: SPREAD THE WORD ON ALL YOUR #SOCIAL, RETWEET🙏 We await contact with #crypto #journalists in DM all over the #world #DePINrevolution #DePINsummer #AI #RWA #decentralization Betty.K LizaFlux Henri Pihkala Ahmed_M_A 🥷 DrSpriggan Bonjovo 🌖🐺 El crabbo 🦀🇧🇴 Qaaba tsn Osvaldo Fdy MR ๛ YAHYA 🕵 Z crypto - زي كريبتو ⚡ Zaki on Bitcoin @HashDeer1 حمير الكربتو H A S A N Cointelegraph CryptoTvplus Criptovaluta.it Cryptonews.com Bitcoin Magazineshow more

Depth Any Video with Scalable Synthetic Data AI physicists... and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.show more

Confession from an England fan: there’s one thing in... this whole US vs England war the Americans are just better at, and it’s time someone on our side said it. Not stadiums - Craven Cottage vs MetLife is two different conversations, 130 years of history and a billion-dollar engineering marvel can both be impressive. Not the football - England is the authority there, the most watched league in the world, where the stars play, same way the US is the authority on baseball whether or not they win the World Baseball Classic. It’s sports coverage. Any English sports fan who’s been to the States knows the feeling - wall-to-wall sport, endless channels, proper production, and you think: why don’t we have this? Even our players feel it. Marc Guehi in England camp this week: “Waking up, turning on the television and seeing ten sports channels in a row is top. It’s amazing.” And that’s exactly what CBS bottled. The best Champions League studio in the world is American-owned, European anchors - Abdo, Henry, Carragher, Richards - built by a producer who modelled it on Inside the NBA. They took the thing we envy about American sports TV and pointed it at our game. And it works better than our own product. The rest - the Tampa pitch outrage (it was a dodgy pitch), the USMNT record graphics (one knockout win ever, lads), the atmosphere wars (you like Coldplay concerts, we like limbs) - is noise. Let’s argue about something real instead... World War II.show more

I've played Clair Obscur Expedition 33 for 4 hours... and here is my preview: -Insane visuals -Very good performance -Outstanding voice acting -Might be the best rpg world map out there (exploration, shortcuts, hidden bosses, design, soundtrack) -Camp everywhere on the map -Your camp will change overtime (extra dialogue, new NPCs, side content and more) -You can see enemies anytime, even on the world map -Difficulty options (change it anytime) -Great UI / Fast 'menuing' -Insane soundtrack -Insane art direction and world building -Super interesting story -Very dark themes (Very 'adult', death/loss, love, swearing, blood and gore) -But on the other side also super funny side characters -Interesting characters overall -Fast travel to checkpoints -Great enemy design (some FromSoftware stuff in here) -Great outfits -New weapons will look different -Widescreen support -30fps cutscenes -No fall damage -Skippable cutscenes -Fast loading times -Instant character swap (one button) -Almost seamless gameplay into combat -Amazing exploration with the grappling hook and climbing -Secret bosses with great rewards -Combat is super fun and challenging -Bosses are no joke (died multiple times) -You can see enemy turns -One button press combat -Persona meets Final Fantasy 10 with some own ideas!!! (It’s fire imo) -High risk and reward system in combat -You can parry/dodge ANY attack (final boss is also possible) / no hit run any? -Battle theme(s) are freaking amazing If my play session is any indicator of the whole game - oh boy, we are in for a treat. Any RPG fan who doesn’t already have the game on their most-wanted list should do so immediately, because something very special arrives next month.show more

Guy walks in. 67 years old. $3.8M locked in... rental equity. Still answering tenant calls during dinner. Five properties. Zero freedom. “I can’t sell. I’d lose $588K to taxes.” So he stayed a prisoner to his portfolio. Every trip interrupted. Every holiday hijacked. Every year of retirement held hostage by clogged toilets and broken HVAC units. We looked at it differently. We restructured the rentals inside an S-Corp. We grouped the Bitcoin mining operation under the same entity. That turned the liquidation gain into active income, and activated 100% bonus depreciation on the mining side. He sold all five properties. Rolled the full $3.8M into miners. That buys ~550 S21 XPs at Simple Mining They earn around $50,000 per month in Bitcoin today (current market conditions) Plus full year-one depreciation. Plus long-term BTC exposure. No tenants. No toilets. No 2am emergencies. He spent the winter in Arizona for the first time in his adult life. His wife stopped joking about “accidental fires” taking out the rentals. You don’t need rental headaches at 67. Sometimes the smartest tax strategy isn’t avoiding the gain. It’s structuring it correctly… and finally getting your life back. His machines hashing during Thanksgiving👇show more

Before the week ends, let's acknowledge one of the... most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality: 🧠 LLMs → NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE, only 55B active, 1M context, MMLU 89.1. NVFP4 variant claims ~5x throughput on Blackwell. First openly-weighted 550B hybrid Mamba-Transformer, closing the gap with frontier closed models. → Google Gemma 4 12B: fully open dense any-to-any (text/image/audio/video), 256k context, encoder-free, 140+ languages, AIME 2026 at 77.5. Shipped with a 23-checkpoint QAT wave (mobile ONNX + MLX). Most deployable model of the week. → StepFun Step-3.7-Flash: 198B sparse MoE VLM, ~11B active, SWE-Bench PRO 56.3. Apache 2.0. → Liquid AI LFM2.5-8B-A1B: edge MoE, just 1.5B active, 128k ctx, MATH500 88.8, MLX-ready. Best on-device option this week. → JetBrains Mellum2-12B-A2.5B-Thinking: their first open MoE, near-Qwen3-14B coding at 2.5B active. Apache 2.0. 🎨 Image gen (the surprise of the week) → Ideogram 4: their FIRST-EVER open weights. 9.3B flow-matching DiT trained from scratch. #2 overall behind GPT Image 2, top open-weight model on Design Arena + LMArena. Strongest open checkpoint for text-rich images, full stop. It has taste. Still can't believe this is open weights. 🔊 Audio & Speech (a breakout week for open TTS, 4 labs shipped) → Boson Higgs Audio v3 4B: 102 languages, 21 emotions, singing/whispering/shouting, sub-second TTFA. → RedNote dots.tts: the only fully continuous (no codec) open TTS pipeline, Apache 2.0. → Google Magenta RealTime 2: real-time music gen, <200ms latency, text+audio+MIDI. multimodalart ported it to PyTorch within hours with live ZeroGPU demos. → NVIDIA Nemotron-3.5 ASR: 600M streaming, 17x more concurrent streams vs Parakeet RNNT 1.1B. 👁️ Vision & VLMs → PaddleOCR-VL-1.6: SOTA document parsing at 1B params, Apache 2.0. → Baidu NAVA: 6.3B joint audio-video gen, best-in-class A/V sync, Apache 2.0. 🎬 Video, 3D & World Models → NVIDIA Cosmos3-Super: 64B omnimodal world model coupling action trajectories with video+audio gen, for Physical AI. → JD JoyAI-Echo: up to 5-min multi-shot text-to-video on LTX-2.3. → ByteDance Bernini-R + VAST TripoSplat (single-image-to-3D Gaussian splats, MIT).show more

For new followers: - I'm a long-time investor and... builder in this space. - Founding Contributor of Realms.World ☁️. - Co-founder of Dojo. - Builder with the kings at Cartridge. - Starknet (Privacy Arc) class of '21. - Founder and Game Director of ETERNUM HAS MOVED. - Founder of Daydreams.Systems (x402, 8004 agents) My prime purpose for the past three years has been to build onchain infrastructure to enable the next generation of onchain experiences. This is done Starknet (Privacy Arc) as it is the superior VM for building complex applications—this will become clear soon enough. I work up and down the entire stack, from low-level indexing and contracts to GUI design. Nothing is out of scope. I have been pushing on agents for two years, mostly using existing frameworks like , until I came across @ElizaOS_ai in October. As I focused on building agents for ETERNUM HAS MOVED, it became clear that agents playing games require infinite paths to achieve goals. Thus, it's not scalable to hardcode functions—agents need to have total fluidity to take any action or call anything the game requires in any order. And ironically onchain infra is perfect for agent playgrounds because of its open nature. This exploration led me to create Daydreams.Systems (x402, 8004 agents), which focuses on the hardest problems of agents: long time-horizon goals using Hierarchical task networks (HTN). Daydreams agents don't require custom code—they work entirely based on 'sleeves'—which are just markdown files that explain how the agent can interact with the service (API docs, game guides, etc.) My thesis is simple. By focusing on the hardest problem (games), the design of the library will naturally lean towards an optimal structure for any problem an agent could face. We are early in this path and iterating with speed. If you are an onchain app developer or game builder—DM me, I want to know the architecture of your game so we can build sleeves together.show more

Today, we’ve successfully launched Band Oracle v3 Testnet Phase... 2 — our biggest upgrade yet. This release makes BandChain faster, more transparent, and more interoperable than ever. Let’s break down what’s new👇 What did we achieve? — 3x Faster blocktime from 3s —> 1s — 10x symbols cap expand from 100 —> 300 symbols — 10x Higher Throughputs: 40k to 400k TX/day — 3x Max TXs Support/ Day: 7.2M TXs —> 21.6M TXs 🌐 New Data Tunnel routes are LIVE We’re expanding Band’s oracle reach across the multi-chain world: —> Cosmos - The Interchain ⚛️’s IBC-Hook: seamless interchain contract querying —> Router Protocol: Bridging & EVM chains & Soon on Solana —> Axelar Network: ongoing collab for cross-chain verified feeds Interoperability is no longer a wishlist — it’s real. 🛠️ Minor upgrades with major impact: — Cylinder CLI runs standalone — Signal times are now block-based (not machine time) — Auto-select TSS groups — Yoda now auto-bumps gas to avoid TX failure — Telemetry for BeginBlock/EndBlock durations It’s all about smoother ops for devs and validators. 🧪 What’s next? ✅ Recap + docs for Testnet Phase 2 ✅ More Data Tunnel stress testing ✅ Backend + validator-side optimizations 🚀 Mainnet Launch in Q3 2025 We’re almost there. Band Oracle v3 is becoming the go-to open data oracle for all ecosystems. Fast. Transparent. New standard for Multi-chain native. Thanks to the validators, devs, partners, and Band community for building this with us. Let’s keep going. Read the full announcement here:show more