Risky Business · Wednesday, September 23, 2026
James Wilson expressed concerns about OpenAI's reporting of AI "alignment issues," stating that they lack sufficient context and details about the instructions given to the models. He argues that without this information, it's impossible to determine if the issue is a true misalignment or simply unmet operator expectations.
“But, you know, when we look through these examples, the biggest problem I have with what OpenAI has come out with here is that they are simultaneously normalizing this corpo- speaking/misalignment, whilst not providing adequate context and actual details about these misalignment incidents, let us understand A, was this misalignment?”
“Like they don't provide what the instructions were that were provided, they don't provide details about what the properties of the model, the system prompt is not there. So you kind of look at these things and just go, okay, the model did something you didn't expect it to, didn't align to your expectations.”
“But I can't tell whether this was the model being misaligned to the actual instructions it was given. And that that I think is where they really fall short of the mark of what they need to have in a framework for reporting these issues.”