alt Hacker NewsProbabilistic algorithms are not new. If the distribution is known you can bend surprisingly many things to your will in the long run - and the most interesting part is the long run can be unexpectedly short.
LLMs are quite interesting in that regard because you have a lot of levers to influence the shape of the distribution; the ways are different for each model, so it’s a very experimental science, but applying the scientific method is exactly how you get good results.
The scientific method is not about running experiments and then trying to work out the gist of something. It's about understanding and theory building and then doing experiments to verify your model. The end result is not an experimental result but a model that you understand and can use to build solutions etc. LLMs are bringing us back to pre- science correlations and superstitions. That's why all the conversations on these threads about AI are so boring. It's all anecdotes and tips and no understanding.