In response to the "wiki incident", OpenAI says it is working on a framework for reporting misalignment incidents during training, evaluation, and deployment (@openai)

@openai:
In response to the “wiki incident”, OpenAI says it is working on a framework for reporting misalignment incidents during training, evaluation, and deployment  —  How we think about the “wiki incident,” where our agents wrote to several internet sites: it's past time for us …

from Techmeme https://ift.tt/lEtcMuQ