|
|
|
|
|
|
by soco
4 days ago
|
|
|
If the AI is not trustworthy, why would be an AI-checking AI more trustworthy? Because they will fail in different ways, so it would (could?) be compensating? And same concept would be using 2 out of 3 tries, or 2 out of 3 models, or whatnot? Isn't this a bit hopeful? |
|
|