Picture for Kevin M. Esvelt

Kevin M. Esvelt

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Add code
Mar 06, 2024
Figure 1 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 2 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 3 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 4 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Viaarxiv icon

Will releasing the weights of future large language models grant widespread access to pandemic agents?

Add code
Nov 01, 2023
Viaarxiv icon

Can large language models democratize access to dual-use biotechnology?

Add code
Jun 06, 2023
Viaarxiv icon

Analysis of the first Genetic Engineering Attribution Challenge

Add code
Oct 14, 2021
Figure 1 for Analysis of the first Genetic Engineering Attribution Challenge
Figure 2 for Analysis of the first Genetic Engineering Attribution Challenge
Figure 3 for Analysis of the first Genetic Engineering Attribution Challenge
Figure 4 for Analysis of the first Genetic Engineering Attribution Challenge
Viaarxiv icon