Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Carol Chen

Carol Chen
Alert button

Constitutional AI: Harmlessness from AI Feedback


Dec 15, 2022
Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, Jared Kaplan

Add code
Alert button

Figure 1 for Constitutional AI: Harmlessness from AI Feedback
Figure 2 for Constitutional AI: Harmlessness from AI Feedback
Figure 3 for Constitutional AI: Harmlessness from AI Feedback
Figure 4 for Constitutional AI: Harmlessness from AI Feedback

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Toy Models of Superposition


Sep 21, 2022
Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg, Christopher Olah

Add code
Alert button

* Also available at https://transformer-circuits.pub/2022/toy_model/index.html 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mitigating harm in language models with conditional-likelihood filtration


Sep 04, 2021
Helen Ngo, Cooper Raterink, João G. M. Araújo, Ivan Zhang, Carol Chen, Adrien Morisot, Nicholas Frosst

Add code
Alert button

Figure 1 for Mitigating harm in language models with conditional-likelihood filtration
Figure 2 for Mitigating harm in language models with conditional-likelihood filtration
Figure 3 for Mitigating harm in language models with conditional-likelihood filtration
Figure 4 for Mitigating harm in language models with conditional-likelihood filtration

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email