> Unless I'm completely misunderstanding how ML works, which very well may be true.
No, you got it right. Describing it as a game of telephone is a great analogy. This is exacerbated by the confidently incorrect problem. LLM output looks sophisticated and correct and may at time actually be correct. However some unpredictable percent of the time it will be incorrect and confidently so.
No, you got it right. Describing it as a game of telephone is a great analogy. This is exacerbated by the confidently incorrect problem. LLM output looks sophisticated and correct and may at time actually be correct. However some unpredictable percent of the time it will be incorrect and confidently so.