im curious too because i am not using ai and now im literally scrutenizing how to even talk here. Even asking ai how this even looks ai? what is even going on here?
I don't like to say one way or the other on things. Especially LLM's. However, if ive learned anything about LLMs and real life problems, is to break it down to the foundation like already mention with weights being compared to neurons and map the parallels.
I found benefit of chaining the task between different LLM's. Claude to Venice, Venice to Perplexity and re framing the intent or misguiding in general still works. Claude is the one that I can feel the guard rails tightening.
we spent a decade killing structured feeds in favor of algorithmic timelines and now we're rebuilding them because the algorithms need structured feeds. the circle of life, but for protocols.