I saw this piece as the start of an experiment, and the use of a "council of AI" as they put it to average out the variability sounds like a decent path to standardization to me (prompt injecting would not be impossible, but getting something past all the steps sounds like a pretty tough challenge)

They mention getting 100% agreement between the LLMs on some questions and lower rates on other, so if an exam was composed of only questions where there is near 100% convergence, we'd be pretty close to a stable state.

I agree it would be reassuring to have a human somewhere in the loop, or perhaps allow the students to appeal the evaluation (at cost?) if they is evidence of a disconnect between the exam and the other criteria. But depending on how the questions and format is tweaked we could IMHO end up with something reliable for very basic assessments.

PS:

> Also if this is about avoiding in person exams, what prevents students from just letting their AI talk to test AI.

Nothing indeed. The arms race hasn't started here, and will keep going IMO.