Hallucinations, like depression, is a multifaceted issue. Training data is only a piece of it. Quantized models, overfitted training models rely on memory at the cost of obviously correct training data. Poorly structured Inferences can confuse a model.
Removed by mod
Hallucinations, like depression, is a multifaceted issue. Training data is only a piece of it. Quantized models, overfitted training models rely on memory at the cost of obviously correct training data. Poorly structured Inferences can confuse a model.
Rest assured, this isn’t just training data.
Removed by mod
I think you are spot on. I tend to think the problems may begin to outnumber the potentials.
Removed by mod
There’s already attempts to create synthetic data to train on