2022 had the highest highs and lowest lows. Really enjoyed going through all of my photos for the year and writing up how I spent it. Excited for 2023 ☺️ https://t.co/2HqwsBkCiT
LLMs generate the answer one token at a time and the second token isn't known as long as the first token wasn't generated. Knowing this is crucial for understanding why LLMs generate nonsensical answers trying to explain unexplainable.
The below screenshot illustrates the problem perfectly. The user asks whether a number prime or not. The LLM generates the first word, which is "No" in this case. That's it. There's no way back. It will continue generating a logical explanation of a wrong answer, which is impossible. The chance of generating a wrong first token is never zero, so the situations like this are inevitable.
And there's nothing to laugh at if you understands how LLMs work.
@flyosity Or it doesn't. There's no way to know without doing the same amount of work it would be without having the AI involved. I don't understand the point if you care about accuracy.