OpenAI is bringing four independent safety evaluators inside its systems
Get Quartz in your inbox
Free daily briefing on global business news.
OpenAI is bringing four independent safety evaluators inside its systems
The pilot assessments cover model alignment, safeguards and monitoring, and give outside experts access to OpenAI's code and training data
SOPA Images / Getty Images
OpenAI signed agreements to bring in four outside assessors — Apollo Research, METR, Transluce and Goodfire — for the first phase of its embedded safety assessments, the company said on Monday.
The assessors will get deep access to OpenAI's internal models and systems to evaluate model alignment and the effectiveness of safeguards over an extended period, the company said. Depending on each evaluation, access includes model checkpoints, source code, training and evaluation data, monitoring systems, technical documentation and discussions with the researchers and engineers responsible for the work.
Apollo........
