DeepSeek-R1-Lite-Preview is live: o1-preview-level performance on AIME and MATHtwitter.com·13 pts·Philpax·2
An Intuitive Explanation of Sparse Autoencoders for LLM Mech Interpretabilityadamkarvonen.github.io·4 pts·Philpax·0
"No way to prevent this" say users of only language where this regularly happensxeiaso.net·10 pts·Philpax·3
Varjo XR-4 Promises Mixed Reality "Practically Indistinguishable from Sight"uploadvr.com·4 pts·Philpax·0