| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://locuslab.github.io/safety-pretraining/
x-github-request-id: 4DAA:3157C7:9126FE:A2F6BB:6952BE8B
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 17:46:52 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210071-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767030413.653372,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: 7b43175f8d36dde8d9339d152e22bc83a2579ef3
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Tue, 16 Sep 2025 13:59:53 GMT
access-control-allow-origin: *
etag: W/"68c96d59-2bb1"
expires: Mon, 29 Dec 2025 17:56:52 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 72C0:292AC1:926770:A437E9:6952BE8C
accept-ranges: bytes
date: Mon, 29 Dec 2025 17:46:53 GMT
via: 1.1 varnish
age: 0
x-served-by: cache-bom-vanm7210071-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767030413.870712,VS0,VE217
vary: Accept-Encoding
x-fastly-request-id: cab4a616d21d354deb11cb5b672735cd13efd9b0
content-length: 3273
Safety Pretraining: SafeLM Models, Data, Benchmarks
SafeLM
SafeLM
Safety Pretraining: Toward the Next Generation of Safe AI
Pratyush Maini*
Sachin Goyal*
Dylan Sam*
Alex Robey
Yash Savani
Yiding Jiang
Andy Zou
Matt Fredrikson
Zachary C. Lipton
J. Zico Kolter
Carnegie Mellon University DatologyAI Center for AI Safety Gray Swan AI
* Equal contribution
TL;DR: We embed safety directly into the pretraining pipeline with data‑centric interventions, delivering a 1.7B parameter model family that is natively safe. Everything (code, data & weights) is open‑source.