Introducing ml-intern, the agent that just automated the post-training... team Hugging Face It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU sandboxes, iterates and builds deeply research-backed models for any use case. All built on the Hugging Face ecosystem. It can pull off crazy things: We made it train the best model for scientific reasoning. It went through citations from the official benchmark paper. Found OpenScience and NemoTron-CrossThink, added 7 difficulty-filtered dataset variants from ARC/SciQ/MMLU, and ran 12 SFT runs on Qwen3-1.7B. This pushed the score 10% → 32% on GPQA in under 10h. Claude Code's best: 22.99%. In healthcare settings it inspected available datasets, concluded they were too low quality, and wrote a script to generate 1100 synthetic data points from scratch for emergencies, hedging, multilingual etc. Then upsampled 50x for training. Beat Codex on HealthBench by 60%. For competitive mathematics, it wrote a full GRPO script, launched training with A100 GPUs on watched rewards claim and then collapse, and ran ablations until it succeeded. All fully backed by papers, autonomously. How it works? ml-intern makes full use of the HF ecosystem: - finds papers on arxiv and reads them fully, walks citation graphs, pulls datasets referenced in methodology sections and on - browses the Hub, reads recent docs, inspects datasets and reformats them before training so it doesn't waste GPU hours on bad data - launches training jobs on HF Jobs if no local GPUs are available, monitors runs, reads its own eval outputs, diagnoses failures, retrains ml-intern deeply embodies how researchers work and think. It knows how data should look like and what good models feel like. Releasing it today as a CLI and a web app you can use from your phone/desktop. CLI: Web + mobile: And the best part? We also provisioned 1k$ GPU resources and Anthropic credits for the quickest among you to use.show more

OpenAI's Deep Research is getting a run for its... money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!show more

I'll always root for a team that open-sources its... best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyantshow 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

I decided to share part of a prompt you... can use to research any protocol in seconds using INFINIT Intelligence by INFINIT. As an example, I used Silo Labs, where I currently farm most of my stablecoin yields. 🔖 Bookmark this + read until the end for a bonus. Just replace [PROTOCOL NAME] with any protocol you want to research. Prompt: "Conduct thorough research on [PROTOCOL NAME] and answer the following questions: - What is the project building? - What problem does it solve, and for whom? - What makes it different from others? - What blockchain is it built on? - Is there a token? What’s its purpose? - How does the protocol work technically? - How does it make money or sustain itself? - What’s the staking model, emissions, burns, and treasury? - Who are the founders, and is the team public and credible? - Who funded it? Who holds most tokens? - Are users, TVL, and volume growing? - How strong is the ecosystem around it? - Who are the main competitors, and how does it compare? - Is the protocol audited? Any past hacks? - What are the best ways to use the protocol (strategies)? - What’s coming next? Key milestones or launches? - What are the biggest risks? - How strong is the community and social traction?" Bonus: Quote this post with a reason why you like INFINIT, and I’ll DM you the full version of the prompt within the next 24 hours.show more

3 weeks since ml-intern launched and we just hit... 1M messages exchanged. that's 3.3 agent-years of ML research in 21 days. 2 months worth of research every day. 17,383 training jobs total. talk about AI acceleration. here's some of what people built: Carlos Miguel Patiño replicated the full DeepSeek v4 architecture and pre+post trained a 100M MoE from scratch. → it landed a third place submission on Keller Jordan optimizer competition. autoresearch on SOTA territory. Lewis Tunstall Got the intern to convert Alec Radford's cool new talkie-lm 1930 model to work with transformers. tokenizer, chat template, model conversion etc all one-shotted by ml-intern. someone created entire PhD dissertation chapter on context-aware agentic cyber defense drafted with 16 research subagents. and someone used it to crack an Paul Jankura kernel optimization take-home. (we don't know how to feel about this one 👀 ) just getting started →show more

We are entering an extremely exciting era for open-weight... models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.show more

BREAKING: Anthropic just dropped Opus 4.8—and it is a... MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:show more

THIS GUY GOT SICK OF UK TRAIN STATIONS HIDING... THE PLATFORM NUMBER UNTIL THE LAST SECOND, SO HE VIBE CODED AN APP THAT PREDICTS IT BEFORE THEY REVEAL IT if youve ever stood in a crowded station like london euston, you know the pain the platform stays hidden until 15 minutes before boarding, then it flashes up and hundreds of people sprint for the same gate so he built something that fixes this: > a clean departures and arrivals app pulling live data straight from the network rail apis > live train tracking so you can watch where your train actually is on the route and whether its running on time > the main feature is a predictive engine that guesses your platform before the station reveals it, and its right about 75% of the time heres how it predicts: every time a train finishes its journey, it logs which platform it actually pulled into and compares that to the platform network rail originally advertised it saves every one of those comparisons, and over time it builds up enough history to predict the platform with a real confidence score he built the whole thing with claude, mostly opus with some fableshow more

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR... is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!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

Building a personal knowledge base for my agents is... increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.show more

What if crypto research was as easy as chatting... with ChatGPT, but powered by real market data👑 Introducing CMC AI, a powerful new tool from CoinMarketCap that combines the speed of AI with the depth of live crypto data. It delivers fast, data-backed answers to your questions: ✅ Want to know why Bitcoin's price is rising? ✅ Curious about the latest news on your favorite cryptocurrency? ✅ Need sentiment analysis? It pulls real-time data and explains it in seconds. But it goes far beyond basic Q&A. In the future, you’ll be able to ask anything! For example, you could ask it to: – Discover undervalued tokens based on volume, MC, and sentiment. – Compare Layer 1s or L2s by adoption, speed, and dev activity. – Detect rug-pull risk via wallet distribution and tokenomics red flags. – Break down your portfolio by risk, correlation, and potential return. – Explore new use cases in DeFi, AI, RWA and DePIN And much more! 🔗Try it here: CMC AI changes how you learn, think, and act in Web3🧠show more

What is the best video editing agent for short... form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!show more

90% of "AI developers" just download pre packaged GGUF... files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.show more

Here's what The Browser Company's AI eng & ML... teams are working on for Dia right now: (This is a pitch to come work for us; info at end) 🤖 COMPUTER USE – we've built our own bespoke APIs on top of Chromium to optimize latency, accuracy, and cost of computer-using agents. Demo attached. Big breakthroughs here in recent weeks. 🛡️ ON-DEVICE MODELS – we've built our own custom infra to run everything from encoder-only models to full LLMs on device. It's cross-platform, supports LoRa adapters, and optimized for the GPU. This system preserves privacy and enables fast inference times. 🧠 MEMORY – with your permission, Dia automatically tailors your AI experiences to you, personally, based on the tabs you open while browsing normally every day. We're also bringing vertical memory to specific features. ♻️ DATA FLYWHEELS – our Fall/Winter P0 is to double-down on training custom models based on implicit signals from daily use of Dia. Dia should get smarter and more useful the more people use it. Whether via RL, auto-generated prompts, or otherwise. If this work sounds interesting to you please visit our jobs page or email [email protected]. Hiring nearly every related role -- from ML engineers to people prototyping with AI and context/prompt writers -- everyone encouraged to apply!!show more

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld... Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.show more

How 2 psyop yourself to success 🍸🥂 Visualization >... + unmatchable lvls of desire (for a specific goal other than money) >> get addicted to work. [ and most importantly DREAM big, DREAM about it, think about it, work for it, and do it every single day, while your sleeping think about it, when you eat, do it, when your walking do it, when your working think about it] In lab studies I’ve compiled tons of data for behavior in hopes of using it for marketing purposes However, it also if curated shows you the triggers people react to The mindset changes that curate and sway them to do more of x (in this case work and create insane drive to achieving a goal or YOUR goals) Remember, every stimuli, every reaction curates your mind. When you come in contact with whatever it may be it sways your future behavior & current attitude/ psychological state So at all times if you want it bad enough you should try to curate your environment (special music that gets you in the mood or NO music, depends on the person bc music distracts you thus means you work less OR if you’re brain storming then it helps) Take out all negative energy, comments, or bs that distracts you and breaks your momentum because one it breaks from the smallest thing then that snowballs and has a negative effect going forward Another thing that I personally like to do is read and put myself into those shoes. For me it’s business and mindset related books and nothing compares to John D. Rockefeller’s mindset, work ethic and GRIT, his absolute desire for SUCCESS : I like his 38 letters to his son, John D the founding fathers of the rockefellers, and a study in power. And most importantly you need to just want it bad enough. Lose sleep for it, not because you want it but because you want it so bad that you’re working nonstop to get to it. This is how Rockefeller succeeded How Elon musk succeeded James Dyson Andrew Carnegie And most importantly how Peter kell succeeded All these billionaires and killers got hyper successful because of their drive and mindsets. It’s so important. If you believe something so strongly it’s revisited your mind to making it reality. Ex. Study DOI: 2003.11.018 > strongly visualizing exceedingly finger abductors boosted muscle strength by 35% Another study showed that basketball players who visualized making free throws showed significant improvement over others. And so on and so on. We as marketers have practiced this forever. We know when we tell a emotional story it changes the viewers mind, and we can lead that into a sale at a much higher conversion rate To get a brutal mindset focused on a dream you have that you truly want with your entire being is the result of the same hormones and neuro pathways after they have been curated and triggered by specific stimuli like in a VSL or ad You need to build your mind, you need to build a dream and want it, give yourself inspiration with books and ideas and positive energy. Build motivation and joy by watching others do it and building proof elements that it can really be done in your mind. Break the barriers and limits Movies are good for this, I like edits for this exact reason because yes it can lead you to doom scrolling but also it can be so so valuable in making you see that goal, want it even more and go for it. I personally really like war dogs, lord of war, limitless, and probably a lot more I’m forgetting. But you get the idea. Your success is in your hands alone, if you believe it fully and truly with a pure heart, then it will happen. Good luck🥂 P.s. * I will drop data, sauce, and more info about this and the methods & stimuli I talked about in this thread continuously so bookmark and come back to check them out.show more

$1,500 → $33,000 on 5min BTC markets in 2... days This is the new reality. It stops being gambling the moment you define an exact algorithm. Here are the recommendations on how to create the same trading bot: → Write your code in Rust – it offers C++ level speed, and there’s an official polymarket-client-sdk available. → Minimize Latency – your trading bot must be deployed in the same data center as Polymarket: AWS eu-west-2 (London). This ensures the lowest possible execution lag. → Price Discovery – Polymarket pulls prices from Chainlink, but Chainlink doesn’t "create" the price; it simply aggregates and broadcasts it. Use Binance – as the largest spot exchange, it is the primary source of price discovery. → Apply the Black-Scholes Model for binary options – this is exactly what will help you identify +EV opportunities by calculating all necessary Greeks and variables. → Don’t turn it into a casino – use the Kelly Criterion. It acts as your risk manager, calculating the optimal % of your bankroll for every single position. If you want to earn like trading bot devs – you need to think like them.show more