Model techniques map
Techniquesevaluationhuman & real-world evaluation

specific method · filed under evaluation

External expert review of safety evaluation methodology

Uses independent external safety experts to review and validate an evaluation methodology.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We engaged a small group of external safety experts (METR, SecureBio, and Daniel Kang) to independently review and validate our malicious fine-tuning methodology.

usedotherOpenAI

Filed alongside

Other methods under evaluation :: human & real-world evaluation.