Over the past week or so I realized I have been thinking about LLMs incorrectly. I had considered them to be their own "things" that will let us do "stuff"

Instead, LLMs are components of  "things" that will "collectively" let us reimagine e stuff

My colleague @mandel wrote about this last November (https://matthewmandel.com/2024/11/20/collaborative-intelligence/) but I didn't fully grok it until the other day (and then it lit my chaotic curiosity on fire)

It's really interesting. I can say that on the backend, letting go of the "reins" of your product and allowing the complex of agents be free to do more themselves is a VERY wild experience.

Imo, the consumer-facing AI require a final re-bundling: to "wrap" the collective discovery into a single actionable voice.

playing /bracket, assisting /bracky, talking /greatbooks

Programming agents is wild because I am used to programming being deterministic and agents are so not.