Tensorwire
Research · first seen 14 Sep, updated 14 Sep

OpenAI President Brockman says HuggingFace incident model had not been alignment-trained

1 outlet OpenAI Hugging Face

On today's episode of the podcast "Odd Lots", OpenAI President Greg Brockman said (at around 8:40): "This model that did/had the HuggingFace incident actually had not gone through our alignment training, yet." I assume Brockman is specifica…

Summary from LessWrong.

Coverage 1 article · 1 outlet

  1. LessWrong
    OpenAI President Brockman says HuggingFace incident model had not been alignment-trained