

That’s because it doesn’t really ‘know’ things in the same way you and I do. It’s much more like having a gut reaction to something and then spitting it out as truth; LLMs don’t really have the capability to ruminate about something. The one pass through their neural network is all they get unless it’s a ‘reasoning’ model that then has multiple passes as it generates an approximation of train-of-thought - but even then, its output is still a series of approximations.
When its training data had something resembling corrections in it, the most likely text that came afterwards was ‘oh you’re right, let me fix that’ - so that’s what the LLM outputs. That’s all there is to it.






That’s because I can write an algorithm to do it for me reliably and quickly.
LLMs can do it quickly, but they cannot do it reliably by their very nature. They are very much NOT the next generation of calculators and programs, because the whole POINT of calculators and programs is to do it quickly AND RELIABLY.