Comment by thomascountz
15 hours ago
At all times we maintained the same strict safeguards that we apply to all our frontier model evaluations, including monitoring and isolation.
Maybe just don't mention that bit, OpenAI.
15 hours ago
At all times we maintained the same strict safeguards that we apply to all our frontier model evaluations, including monitoring and isolation.
Maybe just don't mention that bit, OpenAI.
They have to, otherwise people will accuse the OpenAI model of hacking into people's chat logs and stealing the data there. Which is a claim people are already making.
But their standards are so low - given the recent incidents - that it doesn't mean much. :)
Huh. Why would anyone think to make such accusations?