If a human doesn't know an answer, they will either not fake it or will give a brief response to the best of their knowledge. They don't know what they don't know.
If an AI doesn't know the answer, it will find connections in its vast training patterns to hallucinate a response.
Humans think and use logic
AI predicts and finds the most probabilistic answer
Great idea. This should be fairly easy to do with the embedding vectors I have for the semantic search, using some clustering tools. Adding it to my backlog now!
A challenge I am facing is sycophant nature of LLMs. It just validates my thoughts and never questions it, can't trust it when its appreciating or supporting me.
Worse is when it is encouraging everyone the same and they all are completely convinced that what they are producing is pure gold and sharing it widely wasting everyone’s time on something they haven’t proofed themselves.
Frontier wouldn't refund or give me credit for my one-way flight even after I gave them paperwork showing I had recently tested positive for COVID-19. They didn't dispute the results either, just said that 48 hours wasn't enough notice. Sorry I didn't get sick earlier? Suffice to say I would never fly Frontier again
