Center for AI Safety

non-profit

https://www.safe.ai

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

xksteven updated a dataset 7 months ago

cais/imagenet-o

justinphan3110 updated a dataset 8 months ago

cais/wmdp

justinphan3110 updated a dataset 8 months ago

cais/wmdp-mmlu-auxiliary-corpora

View all activity

Collections 2

models 8

datasets 5

cais/imagenet-o

Viewer • Updated May 27 • 2k • 535

cais/wmdp

Viewer • Updated Apr 27 • 3.67k • 5.63k • 9

cais/wmdp-mmlu-auxiliary-corpora

Viewer • Updated Apr 25 • 8.88k • 76 • 2

cais/wmdp-corpora

Viewer • Updated Apr 25 • 66.4k • 475 • 2

cais/mmlu

Viewer • Updated Mar 8 • 231k • 114k • 347

Center for AI Safety

AI & ML interests

Recent Activity

Collections 2

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

cais/HarmBench-Llama-2-13b-cls

cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors

cais/HarmBench-Mistral-7b-val-cls

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

cais/wmdp

cais/wmdp-corpora

cais/wmdp-mmlu-auxiliary-corpora

models 8

cais/Mixtral-8x7B-Instruct_RMU

cais/Yi-34B-Chat_RMU

cais/Zephyr_RMU

cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors

cais/HarmBench-Llama-2-13b-cls

cais/HarmBench-Mistral-7b-val-cls

cais/zephyr-7b-beta-CUT

cais/zephyr_7b_r2d2

datasets 5

cais/imagenet-o

cais/wmdp

cais/wmdp-mmlu-auxiliary-corpora

cais/wmdp-corpora

cais/mmlu

AI & ML interests

Recent Activity

Team members 7

Collections 2

models 8 Sort: Recently updated

datasets 5 Sort: Recently updated

models 8

datasets 5