Verifying myself: I am rasikabh on Keybase.io. NUyoHatFv9DM-OZoJO2uMiymkDb-1hhrK0Fc / keybase.io/rasikabh/sigs/…

nyu.edu/about/news-pub…

CDS Faculty Sam Bowman recently published his research on how our models learn bias. Read about the press coverage for the paper as well as Professor Bowman’s thoughts about the research in our latest blog post: medium.com/@NYUDataScienc…

#IVoted

Margo St. James, who sought to decriminalize prostitution and make life better for sex workers, has died at 83. An erstwhile sex worker herself, she would begin speeches by saying, "Nice to see so many familiar faces." Obit by Katharine Q. Seelye nyti.ms/3itnZpg

Blog posts on mindfulness in grad school (gradswe.swe.org/gradswe-blog/m…), support from software in grad school (gradswe.swe.org/gradswe-blog/s…), and a pep talk for members who are several years into a long degree (gradswe.swe.org/gradswe-blog/a…)!

Are you an #onlyfans creator? Sign up for our paid ($50/up to 75 min) interview study. We want to understand your digital experiences! bit.ly/OnlyFansStudy

📣ANNOUNCEMENT📣 "Libel Inc: An Analysis of the Libel Site Ecosystem" - Rasika Bhalerao (Rasika Bhalerao), and Damon Mccoy at #WACCO2022

You can (and should) do RL from human feedback during pretraining itself! In our new paper, we show how training w/ human preferences early on greatly reduces undesirable LM behaviors, including under adversarial attack, w/o hurting downstream performance. arxiv.org/abs/2302.08582

Excited to announce our paper Pretraining Language Models with Human Preferences has been accepted as an oral presentation at #ICML2023! 🚀

Registration for SIGCSE TS 2024 is now open! sigcse2024.org/attending/Regi…