After several nights of coding & bug fixing, a... solver for FSI of thin structures on unstructured meshes is finally working, in time for UKACM2025 Conference. Started in 2021; thanks to the Engineering and Physical Sciences Research Council funding, I can work on it now. Much to improve, but this is progress. #SimulationFridayshow more

Lucy Iris out After several days working on this... animation, it’s finally done. I just wanted to do it for fun. You’ll probably notice a lot of mistakes, and I apologize for that, but at the same time I’m really happy I tried it. ☺️ #RezeDance #chainsawmanshow more

An Account on our efforts in fluorescent probes for... plasma & organelle membranes is out in Acc Chem Res ACS Publications. Big thanks to colleagues of my team & collaborators for years of fruitful work! - CNRS Alsace European Research Council (ERC) ANR - Agence nationale de la rechercheshow more

IT support is currently working on fixing the problem.... Thanks for your patience.show more

After 106 unique frames the rough is finally done... 🥹 I still need to work on Mizi and Sua but that's a future me problem for nowshow more

We welcome the additional £3 million in funding announced... by the Chancellor today to support promising early career cancer researchers. This funding from the Medical Research Charities Early Career Researchers Support Fund is a welcome boost at a time when inflation and the cost of living is squeezing research. We look forward to working with the government to put cancer research funding on a long-term sustainable footing and to tackle the more than £1 billion gap in cancer research funding expected over the next decade. #LongerBetterLives #Budget2024 #InTheNewsshow 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

DICE is aware of a bug where weapon models... go invisible just after spawning and/or switching weapons. They're working on a fix. 🐛 Workaround: If this happens, go to textures (in graphic settings) and set it to high or ultra. Thanks NonChergentChef 📽️show more

Im at work and started playing Persona for the... first time but its impossible to navigate anywhere with the fast forward on. Can anybody give me tips and before you say I will NOT turn off the fast forward, this game is too slow and i want to savor my time on this earth. Thanks!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

After staring at Blender's UI for years I started... taking it for granted. But now working on a Godot theme I can't help but notice how ridiculously well-designed it is. It's a fucking miracle this is open-sourceshow more

Belgium's Foreign Minister Prévot in Prishtina: I will actively... advocate for Kosovo's membership in the Council of Europe. Not in the future but now. It is time.show more

I and Jason are currently working on implementing the... CSS `polygon() round` keyword in Chrome. This is one of my favorite CSS features! Thanks to Lea Verou, PhD for bringing it to CSS. The CodePen link is coming soon.show more

Sorry for the lack of posts, I've been busy... with work. I finally got around to updating my blueberry shape, I think this is the perfect shape. (the way he inflates is still work in progress)show more

Return to the Spectrum of Intergalactic Happiness! This album... is something we’ve been working on quietly for years and we’re so happy to finally be able to share with you. We will have more to say about it in the near future but for now we’ll give you the chance to listen to itshow more

Finally this can see the light!! I waited so... much to share my work for #HelluvaBoss S0108! Loved working on this episode I enjoyed every second animating the yellow dog!! She was tough but it's a delight to see a finished shot of her! I love Beelzebub 🥹💛show more

Every single person should build this crypto x AI... workflow. It took me weeks to get this right, and I can't wait to show you guys what I've been building! I started vibe-coding a market-trading/arbitrage/research bot, and the build is finally almost complete. It includes: • Research dashboard for stock analysis • Trading integrations (paper/backtesting) • Risk audits • Daily snapshot • Claude integrations Been chipping away over the past couple of weeks, and can already tell this will take my research to the next level. I'll have a full guide dropping on both YouTube and here on X soon for how to build your own!show more

Anthony Edwards on if Wolves-Nuggets is a rivalry: "Yeah,... for sure. I don't think there's anything else to call it but a rivalry. I think there's a lot of rivalries in the league now, and me and Denver is one of 'em." Wolves vs. Nuggets in the playoffs for the 3rd time in 4 seasons.show more

been experimenting with this for a few hours, lots... of different ideas for how to improve it but here you can rly see how hard it is to move, the only thing i can do is wiggle and flap my hand 😵‍💫show more