today i'm launching Refract. try it here → i... built it because of a small problem i kept feeling while reading research papers. the papers aren't always boring. the ideas can be fucking incredible. but the experience of reading them for hours is. static pages. dense text. equations. figures. tables. references. at some point i realized maybe the problem isn't the research. maybe it's the way we're forced to experience it.show more

Some of the biggest news today is Cloudflare Worker's... Cache. So I built this small catalog to experience it. It allows you to purge the cache for certain pages, or the entire catalog. It also shows you the exact caching headers used. See it in action or try it yourself: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

Maybe the algorithm hasn’t found the right audience yet.... Maybe people just haven’t seen it. But I know one thing, I gave this video everything. And I’m still proud of it. Hopefully more people get to experience it soon Full video link here 🎥show more

Found a great production use case for Jev. I... used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.show more

Ajmer Food safety officials confiscated 2000 plus KG of... adulterated Mithai But the foolishness of the officials can be seen while disposing the adulterated Mithai They have created bigger problem the way they disposed it. I hope there is some rule book on how to dispose it?show more

I just built my own wiki generator plugin for... my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.show more

everyone says Zig is too low-level for simple CLI... scripts. The problem isn't the language. It's the 40 lines of boilerplate required just to fetch and parse a simple API. I got tired of it. So I built gil — a zero-ceremony HTTP client that does it in exactly 3 lines.show more

I wanted to thank you all for the kind... messages for Crosby Deraney and my family. I am still getting around to reading them, but it is taking some time. Today was my first day of sort of feeling myself. Letting go of old routines of the past 16 are so hard. So much love to you.show more

🇺🇸 Execution is what separates success from failure Elon... says his mind is overflowing with ideas, but turning those ideas into reality is the real challenge: "My mind often feels like a very wild storm. I have a fountain of ideas. I have more ideas than I could possibly execute... Innovation is not the problem. Execution is the problem." A reminder that great ideas alone aren't enough, they have to be built. Writer: Valshow more

I decided to see what this led sign would... look like if the quality value was not static but varied from minimal to maximum value. When I added a noise node instead of the value, it was an incredible effect, but I won't show it. Maybe latershow more

what is woonhakie's standard for happiness? 🧸 for me,... even if it is only the tiny spark, even just 1% of happiness comes my way, i try to magnify it as much as i can. i cherish them bcs we live in a world where feeling happy isn't always easy after all.show more

a $400k research analyst at a hedge fund gets... through maybe 15 papers a month a Grok Bot read 3,900 of them last night and pulled out 6 with a tradable rule inside analyst's actual job was never insight, it was filtering - deciding which of ~200 new quant papers a week deserves a backtest that filter used to cost a salary. now it's an api key and one instruction: keep only papers with an executable rule guy running it is 26, no finance degree. built it because arxiv publishes an rss feed nobody in retail bothers to read overnight it pulls every new q-fin paper, strips anything without a testable signal, pushes survivors straight into a backtest 11 weeks. 4,100 papers scraped. 9 came out of sample alive 9 out of 4,100 isn't the bot failing, that ratio is what published quant research looks like once you demand it hold on data it has never seen what kills the other 4,091 is deflated sharpe. run 4,000 variants and something always looks brilliant purely by luck desks have known this since 2014. Bailey's paper is free, sitting on the same arxiv the bot scrapes every night one of the 9 is live on 3 exchanges right now. 0.9 sharpe, nothing cinematic, just real papers were public the whole time and so was the math that filters them. gap was never access, it's that nobody had 4,000 hours to read Grok Bot has 4,000 hours. it spent them last night while you sleptshow more

I miss this, yet don't at the same time.... In terms of Wilds, I do find it interesting that our hunter is less chatty while out in the field compared to Rise, but that isn't a problem. I know hunters talking is a mixed bag for people.show more

i tried Framer Agent to build a brand guidelines... website template, something i've meant to do for a while. a site i can swap a logo, nudge a colour, update the type, and send a link instead of re-exporting a pdf nobody opens. a few observations on the AI process: - i started with references. pulled together a handful of minimalist grid layouts and had Claude describe the visual style back to me. you can do the same inside Framer, feeding it the references directly. - from there i had it write a detailed prompt aimed at that exact style, then asked it to break it into a few smaller steps. then i fed those into the agent, one at a time. - the scaffolding stage is the satisfying part. for something this grid-driven (the columns, the spans, the whole underlying structure) watching it land in seconds is hard to look away from. - but then i still have to sweat the details: text alignment, line-heights, image sizes. i don't mind it at all; it's the part i like, making these design decisions. the strength of the agent is the mundane work. point it at the stuff that eats your time: cleaning up the build, adding responsiveness, dropping in small effects, checking text and colour styles stay consistent, writing alt text for every image. then i get the time back for the parts of web design that are actually fun. 🤝show more

The most surprising demo I had at AWE was... Xelerate VR. This is the best omnidirectional treadmill I’ve ever used, by a mile. Best jumping experience. Best jogging experience. Best running experience. But walking feels bad! Maybe they can fix it one day.show more

Max: “Today I want to gain more racing experience... plus become a bit more comfortable with the car.” “Also because of the track conditions. We just drove a bit in the rain. Hopefully it will dry out a bit soon, but there can always be some wet spots and the grass is still wet.” “So you have to be a bit more careful when you go off line and overtake cars. It is good for me to experience all conditions.”show more

Ryan McMahon was asked what's going on at the... plate: "If I knew, I don't think I'd be in the slow start. I'm grinding. I'm not happy about it, I'm sure other people aren't. At the end of the day, it's about the team winning. I'll keep working and try to turn it around."show more

Wemby on whether Trump going to the game tomorrow... will be a distraction: "Not really. I think it could be, but isolating myself is something I've practiced over the years, and I think I'm good at it, so it's not a problem. This is similar to something media wise, like the Olympics"show more

Aight man they really need to fix the lip-synch... ffs... I can tolerate it most of the time but this is actually ridiculous and it's affecting my experience now :/ It just had to be bad at such a good moment tooshow more