Maria Antoniak

mariaa.bsky.social

18 September 2026 18:28

Our paper: arxiv.org/abs/2606.22748 Wired article:

Nathan Lambert

natolambert.bsky.social

29 July 2026 17:55

New podcast/lecture combo -- a case study in the messy details of Olmo 3 post training & DPO with Scott Geng. It's rare to make time for these discussions. www.youtube.com/watch?v=rhA7...

Maria Antoniak

mariaa.bsky.social

17 February 2026 16:21

I already stopped at Drawn and Quarterly and bought too much, but ok, I will also stop at De Stiil! Thank you!

Nathan Lambert

natolambert.bsky.social

17 February 2026 01:43

Here are my slides from my recent CMU talk, as I'm transitioning from the Olmo 3 era of just building a reasoning model to thinking about how to do impactful research for agentic systems. docs.google.com/presentation...

Brian Christian

brianchristian.bsky.social

05 February 2026 20:07

Reward models (RMs) are supposed to represent human values. But RMs are NOT blank slates – they inherit measurable biases from their base models that stubbornly persist through preference training. #ICLR2026 🧵