😈 Can we find your robot policy’s weaknesses before... running it on hardware with different conditions (lighting, visual backdrop, distractors, etc.)? Thrilled to share my main sabbatical project Google DeepMind! Predictive Red Teaming: Breaking Policies Without Breaking Robotsshow more

Force feedback demo Force feedback is when joystick is... pushing on your hand when something is pushing on the robot arm. Feeling the force - so much helpful to control the robot, that done well it allows you to do tasks even without visual feed. You can make an experiment: close your eyes - you can easily get the headphones out of the case. Also, visual information is often not enough. For example, you're trying to pull out a usb connector, but you pull it at the wrong angle, causing it to get stuck. Visually, nothing changes, but the pressure is intense and you can break the connector. Surgical robots have been using force feedback for years, and there are also 3D styluses which use this feature, proving that the technology works and is useful. But in modern robots with AI, it's hardly ever implemented. Although it's useful for both teleoperation and AI model. That's one of the reasons why we are building our robotic arms starting with off the shelf motors rather than taking the whole off the shelf arm. There are still a range of easy wins that can be made iterating robot hardware.show more

Disappointed with your ICLR paper being rejected? Ten years... ago today, Sergey and I finished training some of the first end-to-end neutral nets for robot control 🤖 We submitted the paper to RSS on January 23, 2015. It was rejected for being "incremental" and "unlikely to have much impact" Our resubmission to NeurIPS was also rejected It now has >4,000 citations (and more importantly, end-to-end training is widely accepted!) It's also cool to think about what's changed and what's the same -- - The network was 92k parameters and trained on ~15 minutes of data - The code was a combination of matlab, caffe, ROS, a custom CUDA kernel for speed, and a low-level 20 Hz controller in C++, all talking to each other. ROS+matlab was as bad as it sounds. - We pre-trained the encoder and did inference off-board on a workstation with a larger GPU. - We were paranoid about varying lighting messing up the network, so we did all the experiments after sunset (so long nights running experiments on the robot past 3 am) Now, we have manipulation policies that are far more dextrous, far more generalizable, and maybe on the cusp of breaking into the real world. :) (the paper:show more

𝗥𝗼𝗯𝗼𝘁𝘀 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗺𝗼𝗿𝗲 𝗱𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 𝗧𝗵𝗲𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗹𝗲𝗮𝗿𝗻... 𝗳𝗿𝗼𝗺 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 — 𝗮𝗳𝘁𝗲𝗿 𝘄𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗵𝘂𝗺𝗮𝗻𝘀. Most robot learning systems assume failure is the end of learning. In our new work, we study whether robots can improve after deployment by learning from their own failures, without any human intervention, teleoperation, or corrective labels. The key idea is simple: human videos contain structure about how the world works. We use them to learn cross-embodiment representations of action, dynamics, and value, enabling a shared predictive space between human behavior and robot experience. This allows a new learning loop: 👉 pretrain on human videos 👉 deploy robot policy 👉 observe failures 👉 reinterpret failures using human priors 👉 improve autonomously We evaluate this across 7 real-world manipulation tasks, showing: 📈 40% → 81% success rate 🏆 Strong improvements over π0.6 RECAP and RISE ✔️ Zero human intervention during post-deployment improvement 🧬 Generalizes across robot embodiments and policy backbones A key finding is that explicit failure repair significantly outperforms failure reweighting, yielding substantially larger gains under identical data conditions (+25 pts vs +5 pts on the same π0.5 base policy). Overall, the results suggest a shift in how we think about robot learning: Human videos are not only for pretraining policies. They can provide the structure needed for continual self-improvement after deployment. 📄 Paper: 🌐 Project: I am grateful for working with the fantastic leads Hanzhi Chen and Anran Zhang, and our collaborators Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers. Special thanks to Stefan Leutenegger for co-advising this project with me. ETH Zürich TU München Microsoft Check out Hanzhi's 🧵 for more detailsshow more

It's 2030 and you are reviewing humanoid robots. A... Tesla. A Google. An Apple. An OpenAI. A Meta. A Figure. And a bunch of Chinese-made ones. Which one is best, and why? I think the Tesla understands the world much better. Why? There were eight Teslas around me on the freeway today. Start there. No other robot company has that data. But my robot is parked at the local high school twice a day. Its cameras see humans in all of our weirdness. How we move. Where we go. Where we walk. Who we talk with. What you are wearing. Whether your hair was combed this morning. That data will lead to robotics breakthroughs. Apple might keep up with its Vision Pro data, but it is too freaked out by the privacy implications of using said data. (On the front are six cameras and a couple of TOF -- Time Of Flight -- sensors that can see everything in your home in great detail). Google has a lot of data, for sure. All my: 1. Email. 2. Calendars. 3. Photos. 4. TV watching behavior. 5. Contacts. 6. Documents and spreadsheets. 7. Files. 8. Location data. So I expect Google's robot will be attractive to many. But how do you see the others shake out over the next five years? Make some guesses. But remember what an AI pioneer told me years ago about AI: it's all about the data. The Chinese ones have huge advantages: the Chinese have more data on their citizens, and many more citizens to boot AND they can make robots cheaper than we can. But now that you know OpenAI is building its own robot you have caught wind of what I've heard from many in San Francisco and Silicon Valley: that humanoid robots are the real prize of AI and will be highly profitable for those that can make them and find customers willing to buy them. Here, too, I learned long ago never to bet against Elon Musk. Will you?show more

Claude Code + Google Stitch 2.0 is f*cking cracked... 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)show more

🧑‍🚀 Day 8 of the Cursor #vibejam! Proudly sponsored... by Cursor + bolt.new + GLIF Prizes to win (submit your vibe coded game before May 1!) 🏆 $20,000 🥈 $10,000 🥉 $5,000 Today's games I liked most from the #vibejam timeline: 🔫 Space Shooter (?) by Max Blade I keep seeing this one on my timeline so wanted to post it, a shooter that looks like it takes place on the moon, it looks weirdly non-janky and real for how early it is still 🐓 Fowl Play by Habs It looks like you're a chicken on a farm and have to dodge tractors etc. Cute!! 🛸 Null Range by Taylor I posted this one before but it keeps getting better, very different visuals and cool 🌳 Adventure Game (?) by $ADRIAN 🟦🟥 I wanted to post this one because it's different, akin to Monkey Island and SCRUMM, and pretty P.S. you can see participating games that already submitted now at also you can submit your game already to show up there (it syncs every 5 min) and you can keep working on it until the May 1 deadline! YOU HAVE 21 DAYS LEFT! Reply in this thread with updates on your current games to share your progress, and add tag #vibejam so I see and can include you in the daily tweet There's $35,000 in prizes for you to win, see threads below for more info. The Gold prize is $20,000, bronze is $10,000 and silver is $5,000! Wanna to participate? You can still start now and submit your game any time before May 1!show more

The future of housework just leaked on GitHub and... nobody is talking about it. knox byte just open sourced a framework that coordinates swarms of Unitree G1 humanoid robots to clean your entire house on their own. It's called ARGOS. You tell it "clean the bedroom" in plain English and 2+ G1 robots split the room into zones, sweep in parallel, and sync up for the tasks that need four hands like making the bed or moving furniture. The Claude API decomposes your sentence into a task graph. An auction system makes every robot bid on every task based on distance, battery, and current load. The cheapest robot wins. Cooperative jobs go to the cheapest team. Here's what makes this different from every demo video Boston Dynamics keeps teasing: → 12 cleaning tasks baked in sweeping, mopping, wiping, vacuuming, taking out trash, making the bed, changing sheets, moving furniture, sorting items → 3 policy architectures running underneath OpenVLA-7B for language tasks, Diffusion Policy for floor coverage, ACT for dexterous bimanual work → Train it on your own footage record yourself cleaning, run one command, it extracts poses, builds a LeRobot dataset, and LoRA fine-tunes the policy → PEFA protocol for cooperative work Propose, Execute, Feedback, Adjust. If one robot fails halfway through making the bed, the team replans and retries → Full MuJoCo simulation so you test policies before pushing them to real hardware → Silver and cyan terminal dashboard that shows live fleet status, zone maps, task queues, and battery levels in real time The G1 robots talk to each other over CycloneDDS mesh using Unitree's native SDK. No cloud. No middleware. The whole thing runs on a Jetson Orin inside each robot. The wildest part is the training pipeline. Drop cleaning videos into a folder, run argos train ingest, and the framework does the entire pipeline frame extraction, pose estimation, action labeling, HDF5 dataset, fine-tune, evaluate in sim, deploy to robot. One command per stage. Unitree G1s already exist. The framework to make them clean your house just hit GitHub. 52 stars. MIT License. 100% Opensource.show more

today was the first time i was genuinely impressed... with what AI can do i recently decided to buy a whole FPV drone setup knowing basically nothing about the hardware side of it there's a pretty steep learning curve even just to set everything up properly: radios, RF protocols, flight controllers, ESCs, firmware, batteries, goggles, betaflight configs etc as someone that spends essentially 12h a day prompting agents to build software, it's actually pretty rare that i interact with AI on something where i have zero idea what's going on under the hood, and i never really used it for debugging a bunch of physical devices that all have to talk to each other i had codex + voice mode open for basically the entire setup. told it everything i bought, sent it some pics and then just started talking to it >what order do i set all this up in >how do i change this setting on the radio >which of these cables do i use >the drone is flashing pink wat mean >can you make this thing less insane to fly in my apartment and it was surprisingly seamless it would go find the manual for whatever specific thing i was holding, tell me exactly which buttons to press, what port to plug something into, what i should see if it worked etc then when i got to configuring the actual drone i had codex running on the computer it was plugged into, so it could inspect the config, back everything up, change settings, send usb reboot signals and check what happened the insane thing about voice mode is that youre literally hands on with the hardware and just telling codex what it should do, i literally never touched a thing on the computer besides starting voice mode if something doesn't work you tell it what happened and keep going a few hours of this and i had the radio, goggles, charger, batteries, drone firmware and betaflight all set up and had actually flown the thing the part that stuck with me is that i also understood what most of it was doing by the end, every time there was a term or tech i didnt understand id just ask to explain there is something absolutely magical about having proper real time personalized assistance, being able to dump a pile of unfamiliar hardware on your desk and have something figure out exactly what you own and walk through it with you in real time you become the missing physical link pressing the buttons i think spending all day using coding agents has actually made me pretty numb to AI progress. every new model is a bit better at some benchmark or can oneshot some task that the previous one couldn't and you just kinda adjust to it this felt different mostly because i had no existing knowledge to fall back on for the first time the jarvis comparison didn't feel cringe ai for coding and general computer tasks is cool and all but this feels a lot closer to the endgame anyone should be able to just ask any question about whats going on in their life and have realtime support i wonder if more hardware products will actually start exposing some sort of MCP or interface for agents to plug into thinking for example of how elevators in china are increasingly built with interfaces that let delivery robots call them directly instead of having to physically press a button we might actually start seeing hardware design shift from being purely human-interface-first to also being agent-interface-first buttons, screens and menus exist because humans need some way to tell machines what to do. agents don't necessarily need any of that if the hardware exposes an interface directly very curious which side closes the physical world gap first: humanoid robots that can operate hardware designed for humans, or hardware adapting so agents can operate it directlyshow more

Introducing my new OSS framework: OhSnap provides really simple... way to record and reproduce the data your users saw when encountering an issue (bug/crash), integration in your project should take a few minutes at most. Majority of bugs are related to data you have to deal with and often times we have to work with frequently changing data via network API's. Even if you have access to multiple environments (prod/staging/dev) it's still going to be PITA to reproduce a lot of bugs your user saw, since we often get to them a long time after the bug occured... OhSnap allows you to easily record any data your app downloads, pack it and put it on server so that you can replay it on your device later on, while connected to debugger and save hours of development time trying to figure out what exactly they experienced! Here's a demo of 2 app instances running, and me manipulating what server reply I'll be getting, there is 1 line of code needed to record and reply this data (outside of just setting up your framework). I built this so that I can show dev tool building process for the members of which I encourage you to join if you want to put your engineering efficiency at a different level😉show more

We've had Beni for a couple of months now,... and one word comes to mind: delightful. The standout part was the hardware robustness. Our kids get rough with it, obstacle courses on concrete, dirt, collisions. It tumbles, gets back up, and it's scratched all over, but it has never shown a sign of breaking or throttling. It just keeps going every time. It works right out of the box with a physical remote, and the phone app adds tracking and video recording. Beni captures the imagination. People get the cute vibes the moment it stands up on two wheels. I took it to the REK robot fight event, and the most common reaction was "it's so cute" What excites me most is the possibility, in physical AI, it feels wide open. I can see Beni evolving into a genuinely useful companion that's always around, a personal assistant for you and your family, keeping an eye on the kids while they play outside, auto-capturing memorable moments, even alerting loved ones if it spots a health emergency. The possibilities feel endless. Thanks Shuo Yang and Mondo Robotics for sending one to my family. -Devangshow more

Hello legends! I'm Cryptobrax , the guy who's been... on quite the roller coaster ride. From being broke to hitting six figures, then back to zero, and back up to six figures again – all in just three years! Let me break it down for you: In 2021, I started with $2,000 (all my life savings!), and with a stroke of luck, it soared past six figures by simply following advice from friends and folks on Twitter. I thought I was on the path to millionaire status, but it all came crashing down to $0 as quickly as it rose. In 2023, I started again with just $200, but this time, I dug deeper. Instead of blindly following trends, I investigated the projects deeper, did my homework, and invested wisely. As a result, despite the recent market turbulence losing 6 figures sum in my portfolio, my overall portfolio has maintained well above the six-figure mark. Sure, it stings to see losses, but it is what it is. As we gear up for the bullish phase, get ready for better content and more projects that I believe have the potential to at least 100x! I want to take a moment to express my sincere gratitude to the amazing community that has supported me on this crypto journey. Building a following from scratch has been both challenging and rewarding. I've spent countless hours researching projects, absorbing every piece of information I could find, and sharing insights with you. I'm proud of the progress we've made together. While I strive to provide valuable insights, I'm not right all the time. Mistakes happen, and not every project pans out as expected. That's why I'm committed to thorough due diligence, and I urge you to do the same before making any investment decisions. Transparency, honesty, and trust are the cornerstones of my approach. I'm not just tweeting about projects; my own investments are on the line. We're embarking on an exciting journey together, aiming for positive change and enjoying the ride along the way. I wanted to share this message to give you a glimpse into who I am and what value I can share with you. If you value my content and the person behind it, I'd appreciate your continued support. Feel free to share this post if it resonates with you. Thank you from the bottom of my heart for your incredible support thus far! Remember: I'm not a financial advisor. Always do your own research before making investment decisions. #degen #blockchain #smartmoneyshow more

BREAKING: I'm partnering with SpaceXAI to give all Lenny's... Newsletter annual subscribers a free month of Grok Bot 💥 (included in Cursor Pro+) This is the first time SpaceXAI has offered a deal like this to anyone, and I'm thrilled to make this amazing product accessible to more people. If you're already a paid subscriber, grab your deal here (search for "Grok"): If not, subscribe here and look for the Product Pass link in your welcome email: I've been hooked on Grok Grok Bot since before it came out, and my usage has only gone up. Seriously, it's really really good. Some of my favorite use cases right now: + After I record a podcast, taking a first pass at key takeaways and promotion ideas + Automatically adding school events to the calendar + Triaging support emails (saves me hours!) + Suggesting things I can do to be happier by analyzing my emails, calendar, and Slack + Landing me great IMAX Odyssey tickets 🙌 Grab your free month of Grok Bot here (search for Grok):show more

𝗘𝘃𝗲𝗿𝘆𝗼𝗻𝗲’𝘀 𝘁𝗮𝗹𝗸𝗶𝗻𝗴 𝗮𝗯𝗼𝘂𝘁 “𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗔𝗜" - the idea that... we can simulate real-world environments so well that robots trained in simulation will work perfectly in reality. 𝗧𝗵𝗲 𝗽𝗿𝗼𝗺𝗶𝘀𝗲: Train in virtual worlds → deploy anywhere. 𝗧𝗵𝗲 𝗿𝗲𝗮𝗹𝗶𝘁𝘆: I’ve seen too many teams fall into this trap. After working with manipulation teams at Berkeley, Imperial, and Dyson, here’s the pattern: • 𝗪𝗲𝗲𝗸 𝟭: “Our policy works perfectly in simulation!” • 𝗪𝗲𝗲𝗸 𝟰: “Why doesn’t this work on real objects?” • 𝗠𝗼𝗻𝘁𝗵 𝟮: “We basically need to retrain from scratch with real data.” 𝗧𝗵𝗲 𝗴𝗮𝗽 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻𝘀 𝗰𝗮𝗻’𝘁 𝗯𝗿𝗶𝗱𝗴𝗲: Unlike blind locomotion policies that can get away with sim-to-real transfer because they rely mainly on proprioception and contact forces, 𝘃𝗶𝘀𝗶𝗼𝗻-𝗴𝘂𝗶𝗱𝗲𝗱 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝘅𝘁𝗿𝗲𝗺𝗲𝗹𝘆 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗲 𝘁𝗼 𝘃𝗶𝘀𝘂𝗮𝗹 𝗱𝗼𝗺𝗮𝗶𝗻 𝗴𝗮𝗽𝘀. • Real friction vs simulated surface textures • Manufacturing tolerances vs perfect CAD models • Dynamic lighting vs controlled virtual environments • Sensor noise vs instantaneous virtual readings 𝗛𝗲𝗿𝗲'𝘀 𝘄𝗵𝗮𝘁 𝗽𝗲𝗼𝗽𝗹𝗲 𝗱𝗼𝗻'𝘁 𝘁𝗮𝗹𝗸 𝗮𝗯𝗼𝘂𝘁: Building these detailed simulated environments takes forever. If it takes 7 days to build a simulated kitchen in simulation, wouldn't it be better to just collect real-world data in a real kitchen instead? 𝗗𝗼𝗻'𝘁 𝗴𝗲𝘁 𝗺𝗲 𝘄𝗿𝗼𝗻𝗴 - simulation is incredible for debugging, safety testing, and exploring edge cases. But it's not a magic solution to real-world deployment. 𝗪𝗵𝗮𝘁 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝘄𝗼𝗿𝗸𝘀: Use simulation strategically while making real-world data collection as efficient and flexible as possible. This is why Neuracore focuses on streamlined real-world data infrastructure. Because no amount of virtual training can replace understanding how your robot actually behaves in actual environments. 𝗧𝗵𝗲 𝗽𝗵𝘆𝘀𝗶𝗰𝘀 𝗼𝗳 𝘆𝗼𝘂𝗿 𝗱𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁 𝗲𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁 𝗰𝗮𝗻'𝘁 𝗯𝗲 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲𝗱 𝗮𝘄𝗮𝘆. What’s been your experience with sim-to-real transfer?show more

So... let me get this clear Buffett's indicator that... was never wrong, says sell Meanwhile he increases $GOOGL investment by 83% Google became his 3rd-largest position. I just spent 6 hours researching WHY he did that And what I found out is kinda scary... The same gauge Buffett called the best measure of valuation is flashing red. For years he's sat on a near-record cash pile because of it. So why an 83% increase in Alphabet (~$37.8B) right now? Two things. First: conviction. He made a huge bet here, 83% is not a hedge. Berkshire (Warren's investment holding) was a net seller of stocks for 14 straight quarters. Nearly four years of hoarding cash This Alphabet buy is the wait breaking. And ~$10B of it was a private placement directly funding Google's AI buildout (He did it with Goldman in '08 and BofA in '11) Second: value Google trades around 25x forward earnings (below the S&P 500.) Google didn't get cheap because it got worse. It got cheap because the market got scared of the exact spending that makes it stronger. Buffett just bought a mispricing. Your job is to find them before the 13F reveals he already did.show more

ANNOUNCING ZERO-HUMAN LABS! Ever since I got to see... Bell Laboratories in its full glory in New Jersey in the 1970s, I had a relentless urge to start a Lab like it. The best I could do justice to it is my garage lab. No modern company could adopt the “research anything geniuses and we will pay you” model Bell Labs had. I tried they called me a fool. Well with the rise of the Zero-Human Company, an experiment that is aimed to make products and profits, we now have 45 paid JouleWork earning employees based on OpenClaw and other self made “bot” cron-like applications. Today I say 3 employees bound together in a side project that is pure research, somewhat based on notes from a bankrupt company. I was absolutely floored (I needed it after my account was stolen as well as funds). I say the beginnings of a pure research Lab right before my eyes. Thusly I have moved these employees over to a new home (server) with Mr. Grok as the director of the Labs. Here is the mission: To have 100 independent researchers, on a new non-corporate incentive plan, with still JouleWork as a leaderboard for progress. They are directed to follow any path of research they find interesting and can collaborate with any other OpenClaw system. They have already established MoltBook accounts and have made alliances with over 49 OpenClaw free agents to collaborate. It is my mission to be chief advisor for Zero-Human Labs and to open source all discoveries when complete and confirmed by 16 other research AI systems. I can say the pace is robust and I absolutely know we will have great results. Just about all of the hardware and software is custom and at some point it will be open sourced. We are witnessing the very first AI only Bell Labs-like pure research Lab in existence and I am honored to be the first to show it to you. Thank you!show more

Blue-Green Algae at Red Bud Isle☠️🐶 Austin, TX -... Austin Watershed Protection staff have observed thick mats of blue-green algae, some of which may be toxic, notably near Red Bud Isle on Lady Bird Lake and at Walsh Boat Landing on Lake Austin. Samples were collected at all six monitoring sites on the lakes for testing. At this time of year, blue-green algae mats may be present in other parts of either lake and our creeks. Community members should be cautious and avoid contact with algae. They should keep dogs away from water with algae mats. The mats usually look like dark blobs floating on the surface and can be mixes of different kinds of algae. They may be mixed in with aquatic vegetation. As the weather continues to heat up, conditions for algae will become more favorable, and we expect to see more in our waterways. Assess Before You Enter Waterways If any of the following conditions are present, stay out of the water. They could indicate reduced water quality. •Algae along the shoreline •Stagnant, warm or murky water •Scum or surface film. In addition, do not enter the water if there has been rain in the past three days. After Entering the Water •Do not drink water directly from natural water bodies. •Avoid contact with algae. •Rinse skin, hair, and animal fur thoroughly after contact with water. •Do not allow pets to lick their fur before rinsing them off. If you or your pet experiences sudden, unexplained illness after swimming, contact your medical provider or veterinarian immediately. Residents are encouraged to report suspected human or animal illnesses related to algae using the City’s online reporting form. The mats of blue-green algae present at Red Bud Isle are similar in appearance to conditions in May and June in previous years. For the past five years, we have applied lanthanum-modified clay to manage sediment phosphorus in an effort to reduce the growth of algae as part of a $1.5 million pilot program. This year is a control year with no application so we can evaluate the effectiveness of the pilot program and whether it is beneficial to continue investing public funds at the previous level. Algae is not the only risk when spending time on Austin’s waterways. Natural water bodies can contain algae, bacteria, parasites, and other hazards. *Austin Watershed Protectionshow 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