Comment Re:Attention Blocks (Score 1) 56
This is why, when I use AIs, I try to use 5 or 6 that operate in sufficiently distinct ways and are trained by different people with different data sets. If all of them agree, when instructed specifically to find defects, that something is valid/good, then I can be reasonably confident that this conclusion isn't a result of a specific defect in training or process but has some level of path-independence.
This does NOT mean that the conclusion actually is correct, it just means that a NN will likely reach the conclusion that it is regardless of any of the mechanisms involved.
I have developed 5 different engineering projects this way. None of them have actually been examined by a real engineer yet. I would love to have a real engineer look at them, precisely because this will give you detailed insights into what an AI system actually can do and what it can't.