by natch on 6/11/2025, 3:09:06 AM
Who says there is one single current approach? I think the current epoch is more like a Cambrian explosion style array of approaches, which will probably last only a few months before being covered over by the next layers of AI impact ejecta on which the stage after that will be built, and so on, ad infinitum.
But yes, no doubt we are missing a lot. Please say more about your experiments.
What if we're optimizing prompts while missing something fundamental about how intelligence wants to interact?
I've been experimenting with letting patterns emerge rather than controlling them, and the results surprised me. Curious if others are questioning our current approach to LLM interaction.