15 citations · 45 across the 6 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CL2022★ 5 cited
Language models are better than humans at next-token prediction
Buck Shlegeris, Fabien Roger, Lawrence Chan +1
Current language models are considered to have sub-human capabilities at natural language tasks like question-answering or writing code. However, language models are not trained to…
cs.LG2022★ 9 cited
Adversarial Training for High-Stakes Reliability
Daniel M. Ziegler, Seraphina Nix, Lawrence Chan +9
In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes setti…