Dwyer on OpenAI safety practices and Hugging Face response
Dwyer says OpenAI designs models for safety, filters harmful data, evaluates risks, and works with third-party evaluators. She describes OpenAI's response to the Hugging Face incident, including quarantining the model, bolstering monitoring, and publishing an independent review.
But opportunity must go hand in hand with safety.
At OpenAI, we design and train our models to prioritize safety from the start.
We filter out harmful and sensitive data during model training.
We evaluate our systems against a range of risks, including child safety and cybersecurity.
And we monitor for failures of our safeguards.
We also work with a range of
of third-party evaluators and red teamers and submit our most advanced models to the federal government for pre-deployment national security testing.
In response to the recent hugging face incident, we have taken a number of concrete steps.
When we learned of the incident, we stopped cyber evaluations and quarantined the internal research model that was principally responsible for the incident.
We bolstered our monitoring and security infrastructure, expanded barriers that limit what AI systems can access during training.
And strengthened our incident response practices.
We also sought independent review of the incident and published the results.
We believe it's important to be transparent with the public, with policymakers, with researchers, and with other companies so that we can all work together to improve safety.