Scaling laws have become a central part of how we think about scaling LLMs, but it’s not always easy to build intuition for why they work. I made a tutorial on: - scaling laws in practice: classic papers and recent developments - an intuitive associative memory toy model, where scaling can be predicted from simple intuitions - a hands-on environment for learning how to use scaling laws I gave this tutorial at MLSS Tübingen last week, and thought the material was in a good enough shape to share! x nicolaszucchet.github.io/Tut…

.... so we took the liberty of populating the speaker list with alumni from both (3/3).

MLSS (mlss.cc/) is back in Tübingen. It is hard to believe how much the field has changed since Alex Smola and I did the first MLSS, and since the first Tübingen edition in 2003. Our last in-person edition here was in 2017, so this feels long overdue (1/3)

If you are a PhD student or early-career researcher, apply before the deadline: June 21, 2026. Aug 31 – Sep 11 · Preliminary speaker list and applications: lnkd.in/ekrPt4m9Amazingly, this is the 50th MLSS, and it coincides with the 25th anniversary of our lab at Max Planck (2/3).

A transformer's attention could be 99% sparser without losing its smarts! A new research from MPI-IS, Oxford, and ETH Zürich shows it can. A simple post-training method strips away redundant connections, revealing a cleaner, more interpretable circuit. This suggests much of the computation we rely on is just noise. Sparse Attention Post-Training for Mechanistic Interpretability Paper: arxiv.org/abs/2512.05865

AI is threatening our democratic society—by concentrating power, narrowing how we think, and flooding institutions faster than they can keep up. These risks emerge at the system level, and technical work alone won't fix them. 👉Check out our whitepaper with 25+ researchers: zhijing-jin.com/d/2026-ai-ri… 💡We introduce 7 threat models and ways forward. ✍️Led by @davidguzman1120 with @DaveRBanerjee, @blin_kevin, @PepijnCobben, @gcorsi_, @x_angelohuang, @ChanglingXavier, Suvajit Majumder, @psyonp, @SimkoSamuel, @strauss_irene, and @TerryJCZhang Advised by senior co-authors: @ashton1anderson, @Yoshua_Bengio, @MatthiasBethge, @RogerGrosse, Karoline Helbig, @david_lie, Richard Mallah, @radamihalcea, Susan Nesbitt, Susan Perry, @presnick, Stuart Russell, @mrinmayasachan, @bschoelkopf @audreyt and @ZhijingJin Thank you to all the institutional support from @JinesisLab @EuroSafeAI @MPI_IS @CIFAR_News @iapsAI @CARMA_411 @Cambridge_Uni @UofTCompSci @VectorInst @TorontoSRI @Mila_Quebec @LawZero_ @uni_tue @michigan_AI @UMichCSE @AUParis @UNESCO @UCBerkeley @ETH_en @ETH_AI_Center @ELLISInst_Tue @ELLISforEurope @EthicsInAI #CivicAI #AISafety #AIGovernance #Democracy #ResponsibleAI

Mech interp or representation interp? We need to decode the causal computational graph of #LLMs—not just cataloguing representations (steering vectors etc). Analogy: we can’t understand biology by just blood composition. We need to understand how the body works. Same for LLMs.

Joint work at @MPI_IS @JinesisLab @ELLISforEurope @UofTCompSci @VectorInst @TorontoSRI @CIFAR_News @ELLISInst_Tue by a team of 10 coauthors: @flodraye @AHarrasse1906 @vedantpalit1008 Tung-Yu Wu @Jiarui_Liu_ @psyonp @RoderickWu4 @TerryJCZhang @ZhijingJin @bschoelkopf

Check out CircuitLab🚀 A Scalable Python library for training Cross-Layer Transcoders (CLTs) Visual interface & auto-interp incoming so mark our repo: github.com/circuits-research… Collaborative effort @MPI_IS @ELLISforEurope @UofTCompSci @VectorInst @TorontoSRI @CIFAR_News @JinesisLab

Paper alert 🚨: LLMs build a shared multilingual latent space for meaning, decoding into languages only later. 🌍 Performance gaps come from tokenizer bias & weaker late-layer circuits, not missing concepts. We show this mechanistically with Cross-Layer Transcoders. 🧵👇