I especially love this diagram.

When reality surpasses fiction! Top: fictional forecast for August 2050, broadcast by French TV in 2014 to warn about the consequences of global warming. Bottom: Real French forecast for yesterday, June 22, 2026.

shamelessly stolen

🎓 Applications are now open for the ELLIS Summer School on Machine Learning & Computer Vision in Munich! Get insights into: → Computer Vision → Machine Learning → Natural Language Processing 📍 TU Munich 🇩🇪 📅 15–18 September ⏰ Apply by 30 June 🔗 https://bit.ly/4vvEzJk

Fund basic research and art. Let the dreamers and tinkerers of your society do their thing. You pay for the possibility of minor and major miracles.

Michael D. Green, PhD@michaeldgreen.phd · 2mo ago

President of MIT not mincing words today in @statnews.com www.statnews.com/2026/05/27/s...

🚨 Last call for applicants interested in #Neurosymbolic AI / #NeSy! We’re still looking for a PhD student or postdoc to join the 🇦🇹 FWF Cluster of Excellence Bilateral AI: www.bilateral-ai.net jobs.tugraz.at/de/jobs/4663... jobs.tugraz.at/de/jobs/71ba... 📅 Deadline: May 31 (just a few days left!)

Robert Peharz@ropeharz.bsky.social · 4mo ago

🚨 Opportunity for #Neurosymbolic AI folks! I’m looking for a PhD student or postdoc to join the 🇦🇹 FWF Cluster of Excellence Bilateral AI (think #NeSy++): www.bilateral-ai.net Feel free to reach out or share 🙌

value-driven transport! a new framework for generative modeling, combining elements of * optimal control / RL * optimal transport * stochastic primal-dual optimization thread about our new work with @pmorenoz.bsky.social (@upf.edu) & Adrian Müller (@ethz.ch) 1/

My first paper with my first PhD student @pedrocvieira.bsky.social just landed on arXiv! 🎉 “Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?” Spoiler alert: the answer is largely no—at least, not much more than a single model does. 🧵👇 📄 arxiv.org/abs/2605.22593

Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?

While deep ensembles are widely considered to be the default method for uncertainty quantification in deep learning, their effectiveness for graph-structured data is often simply assumed based on succ...

arxiv.org

Do you want to connect with the European AI research community? NeurIPS Europe is coming to Paris (Dec 9th-13th) and we are looking for sponsors to help to make it happen. Tiers from Bronze (10k€) to Platinum (60k€). neurips.cc/sponsors/pro... @ellis.eu

We're looking for a new colleague at @amlab.bsky.social: Assistant Professor in AI for Science 🔬🤖 World-class ML research, Amsterdam's thriving AI ecosystem (ELLIS, startups, big tech), and some of the best academic labor conditions in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies...

Vacancy — Assistant Professor in AI for Science (AI4Science)

<p><span>Are you passionate about advancing Machine Learning by integrating insights from the natural sciences? Are you eager to bridge the 3rd (<em><span>computational</span></em>) and 4th (<em><span...

werkenbij.uva.nl

Claude Code has certainly made me write code faster. But it turns out, the bottleneck is still experiment run time and experiment analysis

I’m seeing close to zero reaction/conversation about this on here. This is huge news for open research on language models, especially in the US.

Alondra Nelson@alondra.bsky.social · 4mo ago

Wow a big hit for AI2 and for public interest, open source AI research

Sharing “Neural Thickets”. We find: In large models, the neighborhood around pretrained weights can become dense with task-improving solutions. In this regime, post-training can be easy; even random guessing works Paper: arxiv.org/abs/2603.12228 Web: thickets.mit.edu 1/

🚨2 PhD positions with me @amlab.bsky.social on learning causally grounded concepts 🚨 Are you interested in improving the #interpretability #robustness and #safety of AI by integrating #causal reasoning? Join us in beautiful Amsterdam 🇳🇱🌷🚲 Deadline: 20 April www.academictransfer.com/en/jobs/3593...

2 PhD Positions on Learning Causally Grounded Concepts for Safe AI

Are you interested in improving the interpretability, robustness and safety of AI by integrating causal reasoning? The Causality team in the AMLab group at the University of Amsterdam is looking for 2...

academictransfer.com

You are here

spontaneous symmetry breakdance@t8erboi.bsky.social · 5mo ago

- "it can prove little lemmas. that's neat." (early 2025) - "Well, guess I live in the future now" (Opus 4.5)

Claude just told me to remove an offhand footnote about Anthropic's dealings with the DoW 😱🤨

Spot-on. My work got cognitively more challenging, not less, with LLMs, as much more challenging things are achievable now.

Andy Masley@andymasley.bsky.social · 5mo ago

My post in praise of cognitive offloading andymasley.substack.com/p/the-lump-o...

🧵New paper: "Lost in Backpropagation: The LM Head is a Gradient Bottleneck" The output layer of LLMs destroys 95-99% of your training signal during backpropagation, and this significantly slows down pretraining 👇

Well, this seems like a big deal. arxiv.org/abs/2603.087... "This is the first algorithm that can PAC learn even intersections of two halfspaces in time 2^o(n)."

Learning Functions of Halfspaces

We give an algorithm that learns arbitrary Boolean functions of $k$ arbitrary halfspaces over $\mathbb{R}^n$, in the challenging distribution-free Probably Approximately Correct (PAC) learning model, ...

arxiv.org

LLMs are nothing more than models of the distribution of the word forms in their training data, with weights modified by post-training to produce somewhat different distributions.

Emily M. Bender@emilymbender.bsky.social · last yr.

LLMs are nothing more than models of the distribution of the word forms in their training data, with weights modified by post-training to produce somewhat different distributions. Unless your use case requires a model of a distribution of word forms in text, indeed, they suck and aren't useful.

The AI discourse sometimes seems to center on "Is AI good or is it bad?" I find this framing unproductive. AI is not a fixed thing. I would prefer to ask "How might we use this technology for good, and mitigate the bad?" What a shame if the best use we can come up with is no use at all.

To kick off the PhD journey with @pseudomanifold.topology.rocks: What are the limitations of the WL metric, and what is an 𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘷𝘦 𝘮𝘦𝘵𝘳𝘪𝘤? We answer these questions with our 𝗚𝗿𝗮𝗽𝗵 𝗛𝗼𝗺𝗼𝗺𝗼𝗿𝗽𝗵𝗶𝘀𝗺 𝗗𝗶𝘀𝘁𝗼𝗿𝘁𝗶𝗼𝗻 arxiv.org/abs/2511.03068 @olgatticus.bsky.social, Kavir and @erikjbekkers.bsky.social

Graph Homomorphism Distortion: A Metric to Distinguish Them All and in the Latent Space Bind Them

A large driver of the complexity of graph learning is the interplay between structure and features. When analyzing the expressivity of graph neural networks, however, existing approaches ignore featur...

arxiv.org

"He is from [MASK] [MASK]" → "San York"? dLLMs fail because they ignore token dependencies. This Factorization Barrier arises from a structural misspecification: models are restricted to fully factorized outputs. We break this barrier with CoDD, enabling coherent parallel generation. 🚀

Sam is a snake

Mike Masnick@masnick.com · 5mo ago

My goodness.

time traveler from 12 months from now just sent me this

In light of the current funding situation (worldwide), a modest proposal: instead of pouring billions of dollars into GenAI claiming "it *could* accelerate science and research," consider putting 1% of that amount in what *will* accelerate science and research. Namely, funding science and research.

why do science? it won,t make the model Bigger

X is hiring a creative writing specialist at $40 an hour to make Grok better at writing and a true LOL at the qualifications

New open source: cuthbert 🐛 State space models with all the hotness: (temporally) parallelisable, JAX, Kalman, SMC