Ok, we got our first prediction wrong. Fair enough.... So we're running it back: 4 predictions today, each one made by an AI running 100% on your own device with QVAC. It pulls real team stats, runs 10,000 simulations, shows its reasoning, then commits to a scoreline. Today's 4: 🇺🇸 USA v Paraguay 🇵🇾 🇧🇷 Brazil v Morocco 🇲🇦 🇩🇪 Germany v Curaçao 🇨🇼 🇳🇱 Netherlands v Japan 🇯🇵 The AI's call for each game is in the replies. How many do you think it gets right? Drop your predictions below 👇show more

QVAC is AI without the cloud—modular, local, unstoppable. No... API keys. No gatekeepers. Just pure on device intelligence. What will you build with the QVAC SDK when it drops? 👇show more

🚨 JUST IN: CHINA just released an AI EMPLOYEE... that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.show more

This is the most hilarious thing I saw and... did today Ran gemma-4-12B-coder-fable5-composer2.5-v1-GGUF locally with 8 GB VRAM at 20+ tok/sec Anthropic's Claude Fable 5 launched June 9. By June 12 it was banned. I can't access it. You can't either. But here's the twist: I'm running a model trained on its chain of thought at 20 tok/s on my RTX 4060 8GB. Locally. Offline. No cloud. No export control. Enter: Gemma4-12B-Coder GGUF (Q4_K_M) Base: Google's gemma-4-12B-it Fine-tuned on verifiable Python CoT data: - Primary: Composer 2.5 real reasoning traces (only passing solutions kept) - Auxiliary: Fable 5 used to redo the hard cases Composer missed. Every training example's reasoning led to code that actually ran. No hallucinated logic. Llama.cpp flags: -m gemma4-coding-Q4_K_M.gguf -cnv -ngl 44 -c 64000 -v (huggingface model link in comments) Flag breakdown: -ngl 44 → offload 44 layers to GPU (tune this for your VRAM) -c 64000 → 64K context window -cnv → conversation/chat mode -v → verbose output The irony writes itself. Anthropic spent weeks telling the world Fable 5 (mythos) is too powerful to release. Then released it. Then got banned from serving it, including their own researchers. Meanwhile: a Gemma 4 12B fine tune, trained on Fable 5's reasoning, runs fully offline on my mid range consumer GPU No API. No cloud. Just me and llama.cpp. This is why local AI matters. Check out the model's link in the comments. How's your experience been with this model?show more

I just built a Meta Ads diagnostic in Claude... Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)show more

300 AI AGENTS QUIETLY RUN 99% OF A REAL... COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.show more

Shedeur Sanders isn’t running a 40 at the #NFLCombine... —so as a former NFL Scout, I did the next best thing —I timed him running 40 yards during a game two years ago to see how fast he is. I got 5.37 seconds. I timed him with a stopwatch from his first step at the 50 until he reached the 10. What time did you get? I had to go back two years because Sanders only has one run in his 4 year college career over 40 yards on his ESPN stats page —and it was in this game when he played for FCS Jackson State vs. Southern in 2022. The record for the slowest time at the NFL Combine for a quarterback according to the USA Today is 5.37 by Ryan Mallet.show more

🧑‍🚀 Day 4 of the Cursor #vibejam Proudly sponsored... by Cursor + bolt.new + GLIF So the new sponsor is GLIF: Glif is like Claude Code for AI videos and content generation: you can build launch videos for your game, explore asset styles with 100+ AI models/tools and train it on your favorite workflows via skills! Use it to make trailers, game assets, promo videos and more for your Vibe Jam submission! Tomorrow fabian from Glif will share more to help you create promotion materials for your games! Because it'd be cool if after the Vibe Jam your games will take off and become actual games Again browsing the #vibejam tag on X today and there's so many people building cool, cute and fun games so it was hard, but I picked my favorite 4 ones from today: - A literal 🪰 "fly" simulator, not flight simulator 😂 by Gabriel - What looks like a multiplayer Roman combat simulator by Tim Trussner - LeBeau Motel (another?) Habbo Hotel remix by Vincent - Roomba Wars by Thijs which is descriptive enough to not need an explanation 😁 Reply in this thread with updates on your current games to share your progress! Do you want to participate? You can still start now and submit your game any time before May 1! There's $35,000 in prizes you can win, see threads below for more info!show more

Brazil Week 2.0: The Return to the Frontier 🇧🇷👁️⚡... O enxame está de volta! By popular demand, the UpRock World Tour returns to one of our most powerful hubs. Brazil was so loud the first time, we had to come back to close out May in style. From the streets of Rio to the tech hubs of São Paulo, the signal is stronger than ever. This week in the Swarm (Vol. 2): → 2× Rewards: We're doubling down. Earn 2× rewards all week across the region to celebrate the return. → New Skill: Semantic Video Search: Last time we were here, we were reading the web. This time, we’re watching it. We’re highlighting our multimodal AI—powered by the very devices you're running in Brazil. → The 🇧🇷 Roll Call: Can Brazil break its own record? Join the next livestream for a massive community spotlight. → Secure the Frontier: Tag your Brazilian frens—onboard your circle and secure your 1% lifetime kickback. → Share Your View: Show us how the swarm has grown since our last visit. (Home, campus, or those legendary beach views). Round 2. Bigger energy. Multimodal intelligence. Represent your flag. Fuel the Insight Economy. Dates: May 25-31 UpRock World Tour — Powered by UPTshow more

I haven’t missed a workout in over 10+ years... 0 misses in over 3650 days is great discipline if you zoom out however, that doesn’t mean each workout is perfect, not rested, don’t have enough food, not enough time, etc but none of that matters if you showed up and tried your best finishing this, then flying with the team to vegas for the weekend! we’re focusing on the 1st workout of this 4 week period, attempting to push my limits here, going for 110% attempts usually I stay around 80-90% work for most then try to max out once in a while but we hit our max today!!!! ahhhh find what works for you and stay consistent to it id say it’s been a key factor to an understanding that life and business is a marathon it may not be a sprint but we can work on running on pace faster and without pain health is wealthshow more

Run Gemma 4 26B MoE on 8GB VRAM with... 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the repliesshow more

Axie started in 2018. Creatures you could collect, battle,... and raise while learning about a magical new technology called blockchain. Part of the original concept were axie homes called Terrariums. Places where your axies could live, get stronger, and harvest resources. Battles ended up getting prioritized instead, and Terrariums got shelved. But for eight years, that original idea held a special place in our hearts. Terrariums are a nod to that original dream. We're hard at work and our goal is to deliver the first version in late June. Here's how they'll work on day one: 1. You activate a plot of land. 2. You put your axies on it. 3. Every hour, the world ticks forward on its own. While you're away, your land is working. 4. It earns a reward called bAXS, the in-game currency that feeds back into the broader Axie economy. 5. To stay running, your land burns a fuel called Lunium. You get it two ways: buy packs, or let your land generate it slowly for free. 6. How much you earn scales with your axie power, a stat currently called Atia's Flame. Stronger (collectible) axies earn more points. More points means a bigger share of the prize pool. 7. Each land type has its own pool, split between everyone who owns that type. 8. There will be free terrariums that can be used to earn axie experience points (but not bAXS). These should also be useful for onboarding newcomers. The day-to-day is simple by design as we want to make sure that the gameplay is easy to grasp at first and doesn't become a grind for landowners. Learn more:show more

🏀MARCH MADNESS IS HERE — AND IT’S ABOUT TO... GET WILD‼️ 64 teams. Heart-stopping buzzer-beaters. Epic upsets. The bracket-busting chaos starts today. Together we're building the ultimate community parlay with up to $6,400 in cash prizes on the line in the Round of 64. We’ve split the first 32 games into 4 Regional threads (East, West, Midwest & South) with 8 polls each. Reply to any poll before tip-off with your pick + your Rollbit username for a shot to win $100 per game. If over 50% of you vote for the right team, we'll double it to two $100 winners per game! Tag your squad, cast your vote, and let's see if X knows ball! We'll be back every round with new polls and fresh prizes. LET'S HAVE SOME FUN! 🏆show more

this is the worst local ai will ever be.... it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.show more

Back where it all started 🧡 16 years ago... as a freshman at FLORIDA, I walked into the @ESPNGainesville studios and asked if there were any jobs on the radio. Steve Russell (in the first pic) was kind enough to give me a shot. Today I got to sit next to him again to do what we did so many times while I was in college: talk ball. Years full of hard work, failure, a little success, smiles, tears and lots of lessons learned have gone by but one thing remains the same: I’m extremely grateful for the people who formed the foundation of my career and the place (FLORIDAJSchool) where it happened. What a joy it was to spend time with the future of our business today. You are all stars and I’m proud to call you fellow gators. Your eagerness, dedication and curiosity is a reminder of how lucky we are to talk about sports for a living. It was an honor to spend some time on the campus that built me.show more

NanoBanana 2 just made your static ad agency obsolete.... And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.show more

FABLE 5 + HIGGSFIELD BUILD $35K SITES FOR ~$27.... BUT EVERYONE HIDES THE 4 THINGS THAT BREAK. HERE THEY ARE - WITH THE FIX. everyone shows the finished build. nobody shows where it breaks on the way there. this is what actually goes wrong, and how to fix each one: → BREAK 1: the clips look generic fix: never prompt "cinematic hero video." give Higgsfield the exact beat - "a slow push through fog as the logo resolves." specificity is the whole game. → BREAK 2: the scroll janks on mobile fix: tell Claude to scrub a compressed video, not full-res, and cap ScrollTrigger to 60fps. Lenis + will-change, never raw scroll listeners. → BREAK 3: it loads like molasses fix: one line - "extract frames, convert to WebP, lazy-load everything below the fold." a heavy hero is what kills these builds. → BREAK 4: the polish reads fake fix: film grain, bloom, vignette at 10-15% - not 100%. subtle reads $35k. cranked reads AI slop. taste is the dial. get those four right and nobody can tell it wasn't a studio. CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: - mcp_servers: - higgsfield: - url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. the tools ship the site in an hour. these four fixes are what make it look like it took a month. Follow me, reply "BRAKE" and I'll send you the full step-by-step Playbook. full breakdown in the article 👇show more

This runner at first was caught in a pick... off move by the pitcher. Pitcher throws to first and the first baseman fires to second and the umpire calls him out. He looked safe on the play. However, the umpire admits he was safe but said he called him out because the other team was losing 10-0 in the first inning. He said “he was so safe but I just gave it to them.” Basically saying we gotta’ get the game moving right? Fellow umpires, some coaches and parents said they respect the call and why. But many people said you are cheating that one runner by calling him out. They said no matter the score you have to have integrity even if it is 20-0. They said this is why kids grow up disliking umpires and why parents act the way they do. Tough one- I actually understand where he is coming from but if that were your kid, would you want him called out? I say call the game the right way 100% and let it play out the way it is supposed to. How is the other team supposed to get better if you are giving them calls? Do you agree with the umpire and why he did it? Or, are you totally against that and that should never happen?show more