The most dangerous thing about AI isn’t hallucination. It’s that it stopped showing its work

T2Covered by 1 source · first reported by SEA: e27 / Vulcan Post at 28 Oct, 01:00 UTC

Everyone is worried about the wrong AI failure. For two years, the loudest AI safety conversation has centred on hallucination: the model that invents a fact, a court case, a source that never existed. That risk is real and well documented. But a quieter problem is spreading underneath it, and it…

policy

Sources

• T2The most dangerous thing about AI isn’t hallucination. It’s that it stopped showing its workSEA: e27 / Vulcan Post28 Oct, 01:00