Comment by nsingh2
7 days ago
Their models don't consume encrypted text, it would be absurd to train them to do so. Surely they decrypt the text before feeding it into the LLM, so the contents could get leaked out by asking it.
7 days ago
Their models don't consume encrypted text, it would be absurd to train them to do so. Surely they decrypt the text before feeding it into the LLM, so the contents could get leaked out by asking it.