Your curated collection of saved posts and media
See you this Wednesday at the Ollama Gemma Meetup! 💎 https://t.co/qI6joWw158
See you this Wednesday at the Ollama Gemma Meetup! 💎 https://t.co/qI6joWw158
@_StevenFan Hey https://t.co/bMz30SUkf3
Brain 2.0 is the best AI in the world. For personal and for work. We’ve evaluated it for two weeks and it crushes every benchmark. It’s ambient and always aware of the right context at the right time. I’ll start sharing some magic moments in real time. I was looking for restaurants and Brain knew my hotel. Then it suggested that I cancel my meeting tonight and instead just glance at a cheat sheet it created. I was skeptical but clicked yes anyway. Result was best prep sheet I’ve ever had. And I cancelled meeting.
been using hermes by @NousResearch on telegram and was at the gym today trying to find exercises that target my lower lats — realized there was nothing for fitness on there so i put together a skill that lets hermes search 690+ exercises by muscle group or equipment, look up calories and macros for pretty much any food, and calculate things like BMI, daily calories, one-rep max and body fat % also added a nutrition script so you can compare foods side by side like chicken vs eggs curious to see how it works out when it gets integrated 🏋️, @Teknium https://t.co/ER4XRgEVrb
Finally set up my Hermes Agent today by @NousResearch and i am loving it already
A mech piloted by Tiktaalik, the first fish to go onto land, versus a mech piloted by the moss-like plants that grew on land during the Late Devonian. https://t.co/lmMT4NA6Oq
Grok continues to lead global benchmarks: • #1 in AA Omniscience (lowest hallucination rate) • #1 in IFBench performance • #1 on BridgeBench Reasoning • #1 on BridgeBench Speed • #1 on BridgeBench Lowest Hallucination • #1 in Text Arena (medicine & healthcare) • #1 in Video Edit Arena • #1 in AlphaArena Leaderboard Grok is dominating. 🔥
Elon Musk is right to fight race laws in South Africa. You should too. https://t.co/UgC9YoPRIX
@tonysimons_ I'm using Hermes, but am busy making https://t.co/kiuZ7QXLzb better for the moment, so not elite. (AI news from X). That said, I interviewed @NousResearch's CTO last week and it was information packed: https://t.co/ZqtrW8L0el
"Hey AI prepare me for tomorrow's interview of @NousResearch's Hermes, which competes with @openclaw." "Here: https://t.co/qeOiuNkiG0 " My AI is an agent that https://t.co/xiuJ80Twa9 made for me and that I trained over months. You can't get this from Grok. See you tomorrow.
Grok-4.20 just took the #1 spot in the world for Medicine & Healthcare on Text Arena Grok is already saving lives by identifying critical conditions that human doctors miss. There have been many real cases where Grok saved lives ❤️ Grok is officially outperforming every other model on the leaderboard, completely crushing Claude Opus 4.6, Gemini 3.1 Pro, and all other competitors This is massive. Healthcare is one of the most important fields where humanity needs help, and right now, Grok does it best
Black woman from South Africa: “Black people have been patient enough for more than 400 years of colonialism. We are coming for you, and we are going to get everything that you own.” White people are facing racism, hatred, and brutal violence in South Africa. This is not acceptable. More people should know about the horrible things happening in South Africa; almost nobody talks about it.
Not a good sign for the foundation model companies… https://t.co/xS5RNd8EW0
Not a good sign for the foundation model companies… https://t.co/xS5RNd8EW0
MIT engineers show they can accurately measure blood glucose by shining near-infrared light on the skin. https://t.co/93yNTkI0A6
MIT engineers show they can accurately measure blood glucose by shining near-infrared light on the skin. https://t.co/93yNTkI0A6
@uuidnie Here's what is important from X's AI community today: https://t.co/kiuZ7QXLzb Good for your show.
🌐 The integrated browser in @code now has pinch-to-zoom and zoom shortcuts on macOS, better agent tool descriptions, and more updates. Learn more → https://t.co/290HLseY3y https://t.co/zYrKCTiSgq
excited to share what we have been up to. your iphone’s home screen hasn’t changed in ~20 years. it’s the same static grid of icons since launch with zero awareness of your actual life. @skye is a new agentic home screen for iphone. no telegram. no mac mini. & no claws required. skye is ambient intelligence that just works. it continuously listens to your context & acts on it. it builds your reading lists, gives you personalized weather, drafts email replies, prepares you for meetings & trips, flags suspicious charges, works through your reminders, tracks your health, & gives you one tap intel on wherever you are (restaurants, museums, neighborhoods, etc). all surfaced on your home screen. over the next few posts i’ll break down how it works, why we built it, & why we think it deserves to exist in the world. beta starts today. if you’re on the list, you’ll get access very soon. app store shortly after. deeply appreciate you all following along on this fun little journey. also please join our discord !
👨🍳 https://t.co/n7HVmL7DBb
👨🍳 https://t.co/n7HVmL7DBb
Running OpenClaw on AMD just got a lot easier. New one-click scripts are now available to help you get up and running faster across environments. Whether you're experimenting locally or scaling up, these scripts simplify setup so you can focus on building. For #AMDevs looking to get started quickly: Windows: https://t.co/2LZn2HooH8 Linux: https://t.co/klN4clLWZC Server: https://t.co/fFrvyqrt32
@RhysSullivan i really like this slide from @mitsuhiko. writing small self contained libraries and composing them might be an interesting avenue to explore. deck is https://t.co/jwnWHAbS91 https://t.co/0B2a4r0JRS
Hermes Agent v0.9.0 - “The Everywhere Release” Full changelog below ↓ https://t.co/aG5M6owBNS
Hermes Agent v0.9.0 - “The Everywhere Release” Full changelog below ↓ https://t.co/aG5M6owBNS
https://t.co/NO1ZDFLix7 wow
Hey @dok2001 when can we get an end to end cloudflare cli
Today, we’re launching @autoaicam, a camera that builds personal apps for anything you point it at. How does it work? - Take a photo - Auto picks a Frame, a mini-app built and designed by you or our community - The Frame does something for you: track calories, virtually try on outfits, identify a plant, and much more How many of you have a camera roll full of photos that are really actions or reminders? Auto turns these photos into something useful.
Introducing Mercury. Today, we have two types of “AI teams”: 1. Agents in tabs, terminals, 12 browser windows 2. One workspace. Humans and agents actually coordinated. We built @mercury_build so everyone can be type 2. Drop who you are or what you're working on — we'll build your org and send you your agent team.
We just OCR'd 27,000 arxiv papers into Markdown using an open 5B model, 16 parallel HF Jobs on L40S GPUs, and a mounted bucket. Total cost: $850 Total time: ~29 hours Jobs that crashed: 0 This now powers "Chat with your paper" on https://t.co/G2mDae0uv9 https://t.co/qpz7Q9x8Od
Community asked, we delivered. 🚀 We just released almost 7TB of raw rephrased data from #FinePhrase to enable further experimentation and analysis. Code is also public for full transparency and reproducibility. We're using the new Hugging Face Buckets feature for this release. Unlike git-based repos, buckets provide S3-like object storage with content-addressable deduplication. Perfect for this use case because: - No version control overhead for massive files (7TB would be painful in git) - Fast, mutable storage for artifacts that don't need history tracking - Simple CLI and Python API for syncing, filtering, and browsing - Server-side file copying without re-uploading @ratishsp ran a detailed quality analysis on the dataset and found some interesting patterns. Format compliance on tables was rough, hallucination rates were high across splits. Makes sense since the rephrasing was done by a 1.7B model. Weird thing: models pretrained on this data still hit decent benchmark scores after 20B and 100B tokens, even with the quality issues. We covered some of this in the original blog post, but there's clearly more to understand here. That's exactly why we're releasing everything. If you want to dig into: - How synthetic data quality actually impacts pretraining - Why benchmark performance doesn't always track with perceived quality - Better filtering or multi-round rephrasing approaches - The counterintuitive relationship between data quality and model performance Now you can. Data: https://t.co/DNNKKZEO3H Code: https://t.co/WuqFvYobh9 Curious what you find. Hit me up if you do something interesting with it!
🚨 SUPER GEMMA 4 26B UNCENSORED IS INSANE LLM WIZARD COOKING AGAIN @songjunkr Dropped SuperGemma4-26B-Uncensored GGUF v2 and it’s trending on @huggingface🤗 This thing SMOKES the regular Gemma-4 26B: 🤯0/100 refusals (actually uncensored) 🚀Fixed all the tool-call + tokenizer jank ⚡️90% faster prompt processing 🏆Sharper, smarter, way more capable responses - Perfect local beast for llama.cpp ✅ Runs ~18-22 GB VRAM (16.8 GB Q4_K_M file) - Run on 16 GB GPUs! The 31B version in the works, should be out SOON 🤯 Pull this version on hugging face below 👇🏻
rl for agents is moving fast with open source tools. on april 22 at 5pm cest, we’re hosting a live workshop with lewis tunstall, will brown, ofir press, alex zhang, and more to dig into reward design, rollouts, benchmarks, and real-world agent systems. join us live https://t.co/s2vUgc0uEp
