Pedro Madruga
@pedromadruga.com
AI Engineer (in 🇩🇰 since 2012) • http://pedromadruga.com • Interested in Information Retrieval at scale • Group Lead AI Engineer at Karnov Group Opinions are my own.
After SIGIR2025, I selected the best talks (imo) and summarized them using the Feynman Technique. The output was an overview explained in an incredibly straightforward way. I shared them all here github.com/pmadruga/sig... This year, I'm skipping SIGIR2026 but will probably do the same.
GitHub - pmadruga/sigir2025: Explained (relevant) papers from SIGIR 2025
Explained (relevant) papers from SIGIR 2025 . Contribute to pmadruga/sigir2025 development by creating an account on GitHub.
github.com
Damiano Spina@damianospina.com · 4w agoProceedings of #SIGIR2026 are online: dl.acm.org/doi/proceedi... See you soon in Naarm! @acm.org @acmsigir.bsky.social
"AI is a tool, just like other tools we use. And it's clearly a useful one." Linus 🙏
Linus Torvalds Reaffirms That Linux Is Not "Anti-AI" & Not A "Social Warrior" Project
Overnight Linux creator Linus Torvalds wrote another well crafted message that reaffirms the Linux kernel position of not being against AI and lashing back against some kernel developers that are…
phoronix.com
you 👏🏼 cannot 👏🏼 automatically 👏🏼 detect 👏🏼 plagiarism > the available detection tools are neither accurate nor reliable and have a main bias towards classifying the output as human-written rather than detecting AI-generated text link.springer.com/article/10.1... 1/
Testing of detection tools for AI-generated text - International Journal for Educational Integrity
Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environme...
link.springer.com
Software engineering without innovation is just technical complacency.
MTP is wild. Just a few days after the llamacpp support.
Unsloth AI@unsloth.ai · 3mo agoQwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️ MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change. Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s. GGUFs: huggingface.co/unsloth/Qwen... Guide: unsloth.ai/docs/models/...
So much looking forward to put this on a Raspberry Pi or similar.
Unsloth AI (@unsloth.ai)
You can now fine-tune Qwen3.5 with our free notebook! 🔥 You just need 5GB VRAM to train Qwen3.5-2B LoRA locally! Unsloth trains Qwen3.5 1.5x faster with 50% less VRAM. GitHub:…
bsky.app
Rust implementation for Speech-to-Text based on Qwen3 models by Michael Yuan * Self-contained binary build — no external dependencies * Uses libtorch on Linux with optional Nvidia GPU support * Uses MLX on MacOS with Apple GPU/NPU support github.com/second-state...
GitHub - second-state/qwen3_asr_rs: Rust implementation of Qwen3-ASR automatic speech recognition
Rust implementation of Qwen3-ASR automatic speech recognition - second-state/qwen3_asr_rs
github.com
LibreOffice it is. "Danish government agency to ditch Microsoft software in push for digital independence"
Danish government agency to ditch Microsoft software in push for digital independence
Denmark's digital affairs ministry says it plans to switch to the open source LibreOffice software and away from Microsoft products as part of an effort to make the government more digitally…
therecord.media
Could be interesting, macOS only though but with a small footprint. GitHub - ggml-org/LlamaBarn: A cosy home for your LLMs.
GitHub - ggml-org/LlamaBarn: A cosy home for your LLMs.
A cosy home for your LLMs. Contribute to ggml-org/LlamaBarn development by creating an account on GitHub.
github.com
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
I went from Obsidian after a few years, to Notesnook, to Standard Notes. I am back using Obsidian. I can configure it enough to still keep it minimal while addressing all my use cases. I do notice that the Android version is slower than the iOS one. But manageable.
These are the engineers I like to work with. Boris is (again) on point.
A company's "AI Winter" starts when its AI-based product only has focus on engineering and zero on AI innovation. However, trying to avoid engineering debt creates AI debt. And AI debt has deeper (& longer) consequences due to rapid changes happening in the field. Aim for a balance, always.
The art of (AI) science and engineering - an intro
A few thoughts about SIGIR 2025 and how to apply academic research by experimenting in the industry.
pedromadruga.com
The claude code agent teams feature seems great in theory but there's an upper limit on the cognitive load of reviewing every change each agent makes. I'm still reviewing every single change, yes.
Today's reading item
Sumit@reachsumit.com · 6mo agoDeep Learning to Rank in Industrial Search Engines, Recommender Systems and Online Advertising: An Overview and New Perspectives Surveys deep learning methods deployed across matching, pre-ranking, ranking, and post-ranking stages. 📝 dl.acm.org/doi/10.1145/... 👨🏽💻 github.com/guyulongcs/A...
On Github Copilot's memory system and what their engineering wrote fosstodon.org/@pamelafox/1...
Pamela Fox (@pamelafox@fosstodon.org)
Attached: 1 image GitHub Copilot has a memory system now, and the engineering team wrote a great blog post on how they implemented and evaluated it: https://github.blog/ai-and-ml/github-copilot/build...
fosstodon.org
The best compliment i can give OpenAI's Codex 5.3 is that it feels way more like Claude Code
Quilicura, Chile, one of the communities I wrote about in EMPIRE OF AI, has launched a brilliant initiative to inspire more responsible AI prompting. Today, don't use AI; ask the townspeople instead: quili.ai. So heartened to see this creative act of resistance.
The future of software engineering isn't less human, but more focused on higher-level problem-solving. Engineers will evolve to master AI tools, leveraging them to build more robust, thoughtful solutions. #FutureOfWork 6/6
For all the hate that LangGraph gets, there is a hundred times more people using it in battle-tested grounds (such as gitlab, elastic, klarna, cisco and so on). Also, it's silly to hate a framework.
With the amount of AI-assisted tools for development coming out - thus impacting teams' development practices from the ground up - the concept of cross-functional teams seems ancient. A developer that understands these tools will hardly fit in the same team with one that rejects them vehemently.
Domain driven AI - where domain knowledge drives AI implementations - is the best approach for AI-based products.
Software engineering is, fundamentally, a solved problem. AI Science isn't. The ones who treat AI challenges as software engineering ones are doomed to fail.