𝗡𝗘𝗪 𝗣𝗔𝗣𝗘𝗥:Language models recognize dropout and Gaussian noise applied to their activations. The team introduced an a-semantic perturbation into a language model. See what happened ➡️ lawzero.org/en/publicati... #AISafety #MLSky #LLM #LawZero @yoshuabengio.bsky.social

Took me a while to go through this paper introducing "Epiplexity", but this is really one of the best ones I've read in a while. It introduces a simple, new theoretical angle which explains a lot of the information theory paradoxes in ML - and can have practical impacts too. arxiv.org/abs/2601.03220

Learn more in our blog post, "The Scientist AI: Safe by Design, by Not Desiring": lawzero.org/en/unlisted/... (4/4)

At LawZero, we're rethinking the building blocks of frontier AI to create an intelligent machine that is both highly capable and safe-by-design. We’re excited to share our first blog post outlining some of the objectives and core components of our Scientist AI project. 🧵 (1/4)

LawZero is accepting applications as part of the SPAR Spring 2026 program! If you're interested in studying model awareness or emergent misalignment, you can learn more and apply here: sparai.org/projects/sp26/. Applications are open until Jan 14, 2026.

Hi RL Enthusiasts! RLC is coming to Montreal, Quebec, in the summer: Aug 16–19, 2026! Call for Papers is up now: Abstract: Mar 1 (AOE) Submission: Mar 5 (AOE) Excited to see what you’ve been up to - Submit your best work! rl-conference.cc/callforpaper... Please share widely!

LawZero is accepting applications as part of the MATS Summer 2026 program! If you're interested in contributing to LawZero's Scientist AI program and studying model awareness, you can learn more and apply here: www.matsprogram.org/stream/lawzero Applications are open until Jan 18, 2026.

LawZero is growing fast, and we're always looking for dedicated people to join our team. If you're interested in working on technical safeguards to create safe-by-design AI systems, check out the openings on our website and don't hesitate to reach out to our team! job-boards.greenhouse.io/lawzero

Mila's annual supervision request process is now open to receive MSc and PhD applications for Fall 2026 admission! For more information, visit mila.quebec/en/prospecti...

Establishing where we collectively draw red lines is essential to prevent unacceptable AI risks. See the statement signed by myself and over 200 prominent figures: red-lines.ai

L’ONU se dote d’un groupe d’experts scientifiques sur l’intelligence artificielle

One of the most fun projects I worked on. It's not everyday you can train a neural net on a laptop in a hydroelectric dam to provide commands in real time to start a gigantic turbine! authors.elsevier.com/a/1lfNk3QJ-d...

It was a pleasure to meet Prime Minister @mark-carney.bsky.social and Minister Evan Solomon today as part of an official visit at @mila-quebec.bsky.social with many collaborators from our AI ecosystem. We discussed AI risk mitigation, sovereignty & economic potential among other important topics.

This project was 4 years in the making and it's finally out! We found that controlling vehicle speeds to mitigate traffic across a city can cut carbon emissions between 11 and 22 percent. To do this, we used deep reinforcement learning to optimize one million eco-driving scenarios. 🚗🤖🧠

Eugene Vinitsky: Building capable, controllable simulation agents through reinforcement learning RL4RS Workshop at @rl-conference.bsky.social

📍 The RL4RS Workshop is happening tomorrow at University of Alberta, as part of @rl-conference.bsky.social. Join us for a focused day on real-world applications of Reinforcement Learning. 🗓️ Full Schedule: rl4rs.github.io/RL4RS/schedu... We hope to see you there.

Propose some socials for RLC! Research topics, affinity groups, niche interests, whatever comes to mind! rl-conference.cc/call_for_soc...

We’ve received several requests from authors, and in response, the submission deadline for the RL4RS Workshop at RLC has been extended to June 2nd (Anywhere on Earth). Check out the Call for Papers and submission link below — we look forward to your contributions! rl4rs.github.io/RL4RS/

Reminder that early registration for RLC closes on the 30th! Please register early to save yourself some money and help us get the word out.

🚨 10 days left to submit to RL4RS workshop @ RLC 2025! 🤖💡 Consider sharing your insights if you're working on applied RL in industry, society, or critical systems! Cfp: rl4rs.github.io/RL4RS/call_f...

J'ai très hâte de rencontrer les jeunes de la maison Tangente et de produire avec eux un balado sur l'IA! Merci au projet Mégaphone de m'accueillir dans cette aventure!

The workshop list is one of those things that makes clear why RLC is so good. I can't choose which one I'd want to attend!

We have an amazing lineup of speakers, who will share their experience in deploying RL for power systems, industrial processes, nuclear fusion, logistics and more! Consider submitting!

Really looking forward to the RLC workshop on Practical Insights into RL for Real Systems!

THREAD The Wonderful World of Wikipedia (WWW) If you are of a certain age, Wikipedia has been a constant in your life. It was not always so. Here is a pre-history, a history and potential future of the world's great shared book that we all read and write. Also why is it called "Wikipedia"? 1/30

If you've ever tried to train an RL agent to respect constraints with negative rewards, you may have noticed they tend to get risk averse and conservative (no, not that kind of conservative). 1/8

🇨🇦

🚨🚨 RLC deadline has been extended by a week! Abstract deadline is Feb. 21 with a paper deadline of Feb. 28 🚨🚨. Please spread the word!

Here's the speech if you haven't heard it. 13 minutes of your time. Share it with your American friends and neighbours, because they won't see it otherwise. Circulate it in Mexico and Denmark, France and the UK, Panama and Germany, Poland and Estonia, and especially -- especially -- Ukraine.

Having a lot of fun presenting our work with Hadi on RL for microgrid optimization with industrial constraints at Climate Change AI workshop at NeurIPS! If you are at NeurIPS, come and visit us during the poster session :) @hnekoei.bsky.social @climatechangeai.bsky.social

To learn more about the equivalence we found between Inverse constrained RL and normal Inverse RL come find Adriana and Harley at poster 6612.

If you were at the last RLC NeurIPS event, you know it's not to be missed. Invite any RL researcher you know, no invite-only parties here.

It has worked for text, images, and weather. Why not for power grids? Here's our perspective in Joule for a grid foundation model authors.elsevier.com/c/1kCag925JE... This large research effort will be Open Source, as the GridFM project hosted under Linux Foundation Energy!

The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21! Please help us spread the word. rl-conference.cc/callforpaper...

I'm making an unofficial starter pack with some of my colleagues at Mila. WIP for now but here's the link! go.bsky.app/BHKxoss