Very long winded way of saying if you dont know wtf you are doing you won’t produce anything good with AI.
deleted by creator
Historically, automation are all most efficient when used by experts.
However, the content in this blog is exceptionally jarring promotion of so called “prompt engineering”.
If there are simple univeral principles that can be understood by high schooler can magically make LLM more useful, you can bet it is already built into the harness, or even model.
People cannot prompt like Tao because Tao is incredibly good at mathematics, not because Tao is good at prompting. It is very likely with enough time and energy Tao can find the counterexample himself, most people cannot.
They don’t, they don’t have agency or intelligence.
They use more expert language when the user includes more expert terminology - because that’s the nature of how they use context to generate answers.
You use more expert terms, so they draw on training data from more expert source - sources that contain more of that same language.
There is no thought or agency about it. They’re not “rewarding” anyone. They’re mindlessly reacting based on probability.
I agree with what you said, the problem with it is as the process becomes more refined and the scope of the information it draws upon becomes larger so it appears to more and more resemble conscious thought. My problem is how do you know that is not what we are doing. That throughout our infancy especially but really our whole life our subconscious mind is just learning the likelihood of what the next word is and then passing those complete sentences and ideas to our conscious minds, which then understands that process as thought. There is no doubt when I think ideas just arrive in my conscious mind from my subconscious mind in the same way when I think to pick up a cup with my conscious mind it has no idea about sending messages to the muscle groups in my arm to do that, my subconscious mind understands what my conscious mind wants to do and deals with all the technical side. So how can we know the way the subconscious mind deals with the technical side of thinking is not probabilistic and thoughts formed in this way are passed to our consciousness which then convinces itself it engaged in something very special called thought. That the success of LLM is that they stumbled upon the way our minds actually think and that as the comprehension of the models grow so they will approach conscious thought, with the only difference to organic thought being we can see the behind the scenes working of the subconscious part of the process.
idk but paragraph breaks are a really great tool
