Menin questions companies on undisclosed sandbox escape incidents
Menin asks how many times each company's models gained unauthorized access or escaped a sandbox, and whether any incidents weren't publicly disclosed. Dwyer describes the Hugging Face incident and an ongoing look-back investigation; Graham cites published reports; Friend cites three incidents.
New question.
How many times for each of you has one of your models or agents gained or tried to gain unauthorized access to another system or escape from a so-called sandbox test?
And are there any incidents that you have not disclosed publicly?
I'm going to start with you, Ms.
Weier.
Yes, thank you for the question.
I did want to start by, like the others, clarifying that I don't know the answer to the insurance question, but would like to follow up.
Now, on your question about agents, you may have read in the news that we reported we had an incident with Hugging Face.
As a result of that incident, we initiated a significant set of third-party investigations into what happened, and then we made those results public.
We have also initiated a look-back investigation to try to identify whether there were past instances of what we call misaligned agents.
That investigation is ongoing, but we are committed to continuing that investigation as urgently as possible to notifying potential affected third parties and then to making the results public.
Look, we think transparency here is critically important for policymakers like you, for the public who wants to know whether they can trust our products.
And for the rest of industry so that we can all learn together to raise the science of safety that we've been talking about here today.