Menin challenges companies on delayed incident disclosure
Menin notes each company had rogue-agent incidents that were not promptly disclosed to the public, citing months-late disclosures and a general email to Australia's government. Graham points to published risk reports as evidence of transparency.
Mr.
Graham, do you want to?
Thank you.
Yeah, first, in efforts to sort of quantify these risks, we have a number of quite detailed reports that try to elucidate our entire thinking around this.
We increasingly do risk reports in addition to our normal responsible scaling policies, where we outline notions of our threat models and how likely we think certain types of these threats are likely to come to pass.
And then we look backwards at things that are happening within our own company, and we ask,
What is the likelihood that these threats might come to pass in the future, including forecasting, surveying researchers at Anthropic as well?
And we publish this information.
We share that.
Excuse me, are those reports publicly available that you referenced?
They are, yes.
We report them not just in our what we call risk reports, but also when we launch models, we launch, we release detailed multi-hundred page reports with these.