Your curated collection of saved posts and media
We’re releasing TranslateGemma, a new family of open translation models with support for 55 languages. 🌐 Available in 4B, 12B, and 27B parameter sizes – they’re designed for efficiency without sacrificing quality. https://t.co/SRJzCOAKyG
Maps codebase architecture from a GitHub URL https://t.co/9Xm6HXgVUW https://t.co/p68HTEdBF5
Maps codebase architecture from a GitHub URL https://t.co/9Xm6HXgVUW https://t.co/p68HTEdBF5
R.I.P. basic prompting. MIT just dropped a technique that makes ChatGPT reason like a team of experts instead of one overconfident intern. It’s called “Recursive Meta-Cognition” and it outperforms standard prompts by 110%. Here’s the prompt (and why this changes everything) 👇 https://t.co/caDTB52TS9
tinygrad 0.12.0 is out! No more ShapeTracker, AMD wave visualizer with VIZ=2, NVIDIA support without CUDA, and MI300/MI350 driver. https://t.co/df84HVaaGa
🐦bird 0.7.0: fast X CLI for reading tweets: now with home timeline, news/trending, user-tweets and plenty fixes. Thanks @albfresco @odysseus0z @gakonst and all other contributors who didn't list their Twitter. 😊 https://t.co/O4HZcOYt10
Vibe Coding Robotics Part 6 Built a Theo Jansen's Strandbeest simulator to see how an AI models handle complex linkage systems Built with Gemini 3 UI generated with Nano Banana More details ↓ https://t.co/khuXGY9go6
Here's why most attempts to resize windows on macOS Tahoe fail: https://t.co/vDsJtQYjxo https://t.co/gxZAwmmQda
Library of engineering skills for AI agents https://t.co/Su5dTRj9Ec https://t.co/XUFvRgdIuO
Library of engineering skills for AI agents https://t.co/Su5dTRj9Ec https://t.co/XUFvRgdIuO
🚨 NEW: Apple granted new patent that allows for a technology that eliminates the need for prescription lenses in upcoming AR/XR glasses by correcting all prescriptions including astigmatism on device. https://t.co/gw4YgYIMAm
Cautious Weight Decay is a surprisingly simple technique that has been repeatedly validated in Modded NanoGPT. I expect it will gain serious traction as the default variant of decoupled weight decay https://t.co/BLFSeqrf2w
modded-nanogpt WRs 🤝 Cautious Weight Decay Pretty much all the @speedrun WRs since November have used CWD in some form (e.g., @varunneal's "CWD w/ schedule"). Huge thanks to everyone experimenting and sharing results — shoutout to @varunneal, @classiclarryd, @ChrisJMcCormick,
Did some statistics. My productivity ~doubled with moving from Claude Code to codex. Took me a bit to figure out at first but then 💥 https://t.co/cfyKg0E1hf
Someome made a morning report skill and I just gave @clawdbot the tweet and it set up the skill + cron job. https://t.co/CXo0xMGcFv
Cowork but with local models not to send all your data to a remote cloud! https://t.co/2OrBMMO3NJ
In Cowork, you give Claude access to a folder on your computer. Claude can then read, edit, or create files in that folder. Try it to create a spreadsheet from a pile of screenshots, or produce a first draft from scattered notes. https://t.co/GEaMgDksUp
Cowork but with local models not to send all your data to a remote cloud! https://t.co/2OrBMMO3NJ
Codex team is at it again with just another insanely useful feature. If you see your agent going off the rails, or needing some addt'l context, you no longer need to stop the agent. Follow up prompts while the agent is working now inserts the prompt at the next thinking step, allowing it to pivot or provide better outputs without actually stopping the agent. This is undoubtedly a token and time saver. You can still queue up prompts using Tab. Well played!
We’re releasing Action100M: the largest open dataset of ~15 years of video with dense action + caption annotations. It's a key ingredient behind VL-JEPA, now open to fuel the next generation of VLMs, World Models, and Robotics policies. Dataset on HF: https://t.co/bUs67QyOdd https://t.co/IzoGNUXzbJ
We release Action100M, the hero behind VL-JEPA. It is a large dataset with O(100 million) dense action annotations on HowTo100M procedural videos. We hope it serves as a robust data foundation to advance physical world modeling research.
I wrote an interactive article explaining the geometric intuition behind Rectified Flows. I visually explain why flow-models tend to learn curved trajectories, why this is bad for sampling latency, and a relatively simple technique for mitigating it. Check it out! Link 👇 https://t.co/X7nPye8fuJ
Bun — the blazing-fast JS runtime that's eating Node.js's lunch — already ships great llms.txt docs to supercharge your AI coding assistant. Discover these llms.txt files effortlessly while you browse: → llmsdottxt ◎ Open-source Chrome extension that auto-detects llms.txt files, shows a red badge, lets you copy URLs/content instantly, and keeps a history. Perfect for Cursor, Claude, Windsurf, etc. https://t.co/nIBqwIjs3T Give it a try & star if it helps your workflow! ⭐
ScaledML is back! After a 6 year hiatus. Consistently 2-3 years ahead of where ML will be. Examples of foresight at SML: - OpenAI in 2016,2017,2019 announced GPT-2 & RL efforts - Turing award for Deep Learning announced by Turing award winner on morning of award - Groq chip (acquired for $20bn) released - All Google TPU versions detailed Join us on January 29th at the Computer History Museum!
ScaledML is back! After a 6 year hiatus. Consistently 2-3 years ahead of where ML will be. Examples of foresight at SML: - OpenAI in 2016,2017,2019 announced GPT-2 & RL efforts - Turing award for Deep Learning announced by Turing award winner on morning of award - Groq chip (acquired for $20bn) released - Google TPU arch Join on Jan 29 at Computer History Museum!
CTO and Founder of Cerebras will be at ScaledML https://t.co/WoH27Uxx6q
can we go back? https://t.co/ePsrW4P5XD
🖤 https://t.co/bXGfPfQtlE
Stoicism 101: You are not required to have an opinion on every controversy. In fact, you’ll be much happier if you don’t. https://t.co/KXkPgZByU3
#reallifedataviz https://t.co/l415d8BEdB
'How Much Grams?' A mini eval inspired by that viral guy who would ask ChatGPT voice+video to guess the weight of things. Flash crushes it - both speed and accuracy. Post: https://t.co/HNJWhGQIEb https://t.co/191EqCtbnt
Data from my sleep tracking came in handy recently: can you see which 5 days my wife tried a new feather pillow? (Graph shows my snoring duration) A similarly stark positive change came from running an air purifier. Probably lots more places I'm unknowingly sub-optimal... :) https://t.co/PdjHZrxMyI
@ATinyGreenCell I'm trying a https://t.co/ZWqHLe1GOr for similar reasons
It is November 2022, you yap "LLM cant reason because they are autoregressive!! We need cat level intelligence, neuro-symbolic AI! Chatgpt is fun toy product!" It is year 2026, they solve conjectures in 40 min. You literally share proof of open problems with chatgpt links. Actually insane timeline.
I've solved a second Erdos problem (#281) using only GPT 5.2 Pro - no prior solutions found. Terence Tao calls it "perhaps the most unambiguous instance" of AI solving an open problem: https://t.co/TBiCwiSFzl
Saturday hobby fun: biolistics tests with different nozzles, sticking DNA to carriers, and making a computer-controlled pipette for moving microliters of liquid around 😁 (Also breakfast date, happy walks with toddler niece, fireside reading - perfect Saturday) https://t.co/eNM9l57uiZ
