Rasmus Aagaard

I tried deploying DeepSeek-v4-flash-1017 on Azure to try it out in OpenCode. I kept getting an "unknown_model" error code. Searching online I found another person with the same issues with a similar reaction as I'm currently having

Endelig

while you port and emulate games, I ported Jira to my PSP

Finally got to put together a complete deck on the state of open models. What they are, licenses, how competitive they are, signs people are using them, distillation's impact, and how we balance the risks and benefits of openness! natolambert.com/slides/2026/...

As a former Runescape addict and current AI agent addict I really appreciate everything about this video youtu.be/cNm4zyUtWj0

Presented some initial work around benchmarking quantized coding agents at D3A:)

NobodyWho in 25 seconds 🎬 Run open-weight AI models fully offline: 💬 Text generation 🖼️ Image + audio ingestion 🔊 STT, TTS & VAD 🔎 Embeddings & RAG Python, Flutter, RN/Expo, Swift, Kotlin, Godot... No cloud. No API keys. Open source. docs.nobodywho.ooo

All-new trailer for Nathan Fielder and Lance Oppenheim's 'You Can See Everything.' The Elizabeth Holmes documentary is in theaters on October 16.

As I'm approaching the end of my 1st year as a PhD student I'm struggling a bit with how coding agents affect my learning. In that light I found Tim Dettmers' new post very good and inspiring! "Let go of how you work. Not who you are." timdettmers.com/2026/09/21/d...

Happy to announce the sixth session in Copenhagen Advanced Machine Learning Study Group (CAMeLS-Group 🐪). If you live in Copenhagen you are welcome to drop by and read the magnificent paper Bayesian Learning via Stochastic Gradient Langevin Dynamics by Max Welling and friends. luma.com/mhattbxq

Had a really good time at the Danish Data Science Academy's Pre-Graduate retreat :) Was invited to participate in a panel discussion about the different ways of doing a PhD, representing the industrial PhD programme. Can highly recommend it if you’re a MSc student!

Embedding models keep getting cheaper - what required ~300M parameters three years ago now requires only 11M. In practice, that means that what runs on the server today could run in the browser tomorrow.

Me and my agents, just out of frame, are having fun in this harness, laughing

NobodyWho Chat is live on iOS & Android! 🥳 A fully offline AI assistant. No internet, no accounts, no cloud. Run #Gemma, #Ministral, #Granite, #LFM, #Qwen and more, entirely on your device. Vision and hearing support included. Fully open-source. Links in comments 👇

I guess my account is now dedicated to posting my latest dyno #bouldering

That first move took about a million attempts #bouldering

Probably my hardest climb so far. Super stoked:) Guess the grade? 🧐 #bouldering

The Danish Foundation Models (DFM) project is adapting our modular FlexOlmo architecture into a lighter-weight system that runs on commodity hardware—putting collaborative model building within reach of smaller research groups & organizations. 🧵

Got an extended abstract paper accepted at the GLOW workshop at IJCAI :) Turns out you can just delete 6 layers from the Whisper encoder and it doesn’t hurt transcription performance all that much (but you have to be pretty specific about which layers)

new post: how I develop recently using local models. the tooling is now good enough to do agentic workflows and everyone should give them a try! vickiboykis.com/2026/06/15/r...

The machine learning circle of life

Seeing how SOTA models are evolving: becoming more restrictive in usage (decided by the company), less transparent (you cannot tell if the AI lab nerfed your model) + less private (your prompts are stored, no opt out) makes me much more interested in open models + local inference

Magtudredningen: De sociale medier udfordrer demokratiet - og politikerne er medskyldige

getting your weights quantized probably feels amazing for the larger model

new QAT quants are available now if you want to run Gemma 4 12B in only 6.7 GiB VRAM blog.google/innovation-a...

youtube.com/watch?v=f2i0...

Very strongly recommend breaking out of the token discourse and touching grass from time to time to maintain a grip on reality

Legitimately feels like an unquantifiable vibe shift the last few weeks where the pendulum is swinging back to reasonable takes and people experimenting with model choice 🙏

Today we're announcing our #ReactNative bindings for NobodyWho! 🎉 Run #LLM models offline in your #react apps for #Android and #iOS. No internet. No API keys. No usage fees. Fully open-source. www.nobodywho.ai/posts/announ...

We've recently implemented the fastest static embedding model in the world by an insanely large margin Read on for additional info ↓

Researchers identifies "Super Weights" which are at most a handful of weights (amongst billions!). Models end up generating complete gibberish if these weights are removed, underlining the brittleness of LLMs and importance and careful consideration of outlier features. arxiv.org/pdf/2411.07191

For a recent lab meeting, I wrote up a grab bag of ways to think about your development as a researcher during a PhD: emerge-lab.github.io/papers/an-un... Sharing in case folks find it useful or have feedback!

Flash-KMeans An IO-aware implementation of exact k-means that rethinks the algorithm around modern GPU bottlenecks. Flash-KMeans achieves 30x speedup over cuML and 200x speedup over FAISS. Paper: arxiv.org/abs/2603.09229 Code: github.com/svg-project/...

AI i valgkampen: Hjælper det kandidater, eller skræmmer det vælgerne væk? #dkvid #dkforsk

Claude Code Copenhagen meetup 🍻🚀

Together with fellow ddsc.io members I helped a bit with this piece on @ing.dk :)

First blogpost of my cofounder post-Delhi on the deafening silence of public/political sphere as we come closer to another industrial revolution. anastasiastasenko.substack.com/p/the-countr...

LLM cloud inference dominates usage, but should it? Local models and accelerators have improved massively over recent years. Perfect routing to best local model "reduce energy consumption by 80.4%, compute by 77.3%, and cost by 73.8% versus cloud-only deployment" arxiv.org/pdf/2511.07885

Introducing ✨Tiny Aya✨, a family of massively multilingual small language models built to run where people actually are. Tiny Aya delivers strong multilingual performance in 70+ global languages in a 3.35B parameter model, efficient enough to run locally, even on a phone.

Excited to be in fantastic company amongst the speakers for IDA Driving AI 2026 :) ida.dk/driving-ai/t...

Due to residual structures in Transformer-models it's possible that many layers contribute very little to the downstream performance of the network, allowing for removal those redundant layers with little impact. openreview.net/pdf/72eeca23...

Local AI inference through the browser is great. Transformers.js makes it feasible for someone like me who has little web dev experience :) Here's a simple transcription tool using Whisper-large-v3-turbo, making use of your local hardware and ensuring privacy. rasgaard.com/webai-stuff/...