|
|
|
|
|
|
by vrighter
525 days ago
|
|
|
Once I was high and thought of hallucinations as "noise in the output". From that perspective, and the fact that LLMs are probabilistic machines, then halving the noise would probably involve 4x the computation needed. Which seems to track what I observe. Models are getting MUCH larger, but performance is practically at a standstill. |
|
|