Profile avatar
blackhc.bsky.social
My opinions only here. πŸ‘¨β€πŸ”¬ RS DeepMind Past: πŸ‘¨β€πŸ”¬ R Midjourney 1y πŸ§‘β€πŸŽ“ DPhil AIMS Uni of Oxford 4.5y πŸ§™β€β™‚οΈ RE DeepMind 1y πŸ“Ί SWE Google 3y πŸŽ“ TUM πŸ‘€ @nwspk
68 posts 4,105 followers 1,948 following
Getting Started
Active Commenter

I am quite excited that our brand-new module "P79: Cryptography and Protocol Engineering" has its first lecture today! @martin.kleppmann.com and I designed the course to bridge the gap between mathematical ideas and the challenge of implementing secure cryptography in the real world. @cst.cam.ac.uk

Check out MODEL SELECTOR, a framework for label-efficient selection of pretrained classifiers. We reduce the labeling cost by up to 94.15% to identify the best model.

Ever wondered why presenting more facts can sometimes *worsen* disagreements, even among rational people? πŸ€” It turns out, Bayesian reasoning has some surprising answers - no cognitive biases needed! Let's explore this fascinating paradox quickly ☺️

TMLR is now on Bluesky: be sure to follow @tmlrorg.bsky.social!

Ever wondered why presenting more facts can sometimes *worsen* disagreements, even among rational people? πŸ€” It turns out, Bayesian reasoning has some surprising answers - no cognitive biases needed! Let's explore this fascinating paradox quickly ☺️

I didn't talk about it but I also made heavy use of Claude 3.5 and also o1 and Gemini when creating my lecture series on info theory and active learning in 3.5 weeks: bsky.app/profile/bla...

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now πŸ₯³ They cover quite a bit from basic information theory to some recent papers: blackhc.github.io/balitu/ and I'll try to add proper course notes over time πŸ€—