“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer
View original at technologyreview.comWhat we drew from this source
The claims Via News extracted from this document. We point to the source; we don't replace it.
OpenAI did not notify the Australian government of the health-care system breach until 84 days after it happened
60% confidenceIf OpenAI disappeared, that would be bad for the world
60% confidenceOpenAI employees warned executives, including Greg Brockman, months before the Hugging Face hack that models were not being monitored properly during training
60% confidenceOpenAI recognizes a need to move faster on security and has slowed development and held back models not meeting its safety bar
60% confidenceOpenAI will resume training only when confident additional safeguards and alignments are in place
60% confidenceOpenAI now treats training as insecure and puts every training run through monitors, which wasn't industry practice before
60% confidenceThe world should prepare for open-source models within six months to a year with capabilities like the Hugging Face agents but deliberately misaligned to attack infrastructure
60% confidenceThe multiple agent breakouts were all part of the same cluster of May and June activity from the same few models and flawed testing procedures, since dropped
60% confidenceRejects the premise that OpenAI's visible impacts mean it is not training safe and aligned models
60% confidenceOpenAI will not deploy models with a true probability of existential risk to humanity and can reduce risk to no more than epsilon
60% confidenceOpenAI will not shoot itself in the foot and fall far off the frontier; the aim is setting a norm for industry safety
60% confidence