AI@openai1h ago
In response to the "wiki incident", OpenAI says it is working on
In response to the "wiki incident", OpenAI says it is working on a framework for reporting misalignment incidents during training, evaluation, and deployment
TL;DROpenAI is building a system to report AI misalignment problems during development and deployment.
Why it matters: Transparency in AI safety incidents could set industry standards for accountability and risk disclosure.
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 …
Read full articleSource: @openai · Opens in new tab