atriarch

It's nice to see human-centered computing making a comeback with the older, robust, and hefty tactile interfaces - and I hope to see more like this as token factories eat wallets and jobs.

Someone still has to orchestrate. I read every decision the LMs make and will stop and pause it and test it's assumptions and output. Sure that will occur less and less, and the feedback loop may go up a few levels (I.e. it breaks in production and requires a team of investigators, a code detective, and a techno-theologist, perhaps), but the feedback from the real world (nature vs nurture) will still occur. The laws of thermodynamics and system equilibrium still apply, and the need for those to architect and orchestrate will still be needed.

In the future, I see a small percentage of benevolent system-thinkers, hackers, and architects still at the helm. And, even if 95% of the time they are the guy who feeds the dog that protects us from touching the machines, occasionally nature will force us to convene and tell the machines what to do (or at least bargain with them).

The rest of humanity will go back to the default state: digging potatoes out of the ground in a village of 200 down by the river.

Exponential growth is the path of longsuffering, and one doesn't always make it. It sucks and looks and feels bad for all involved. This is why advice such as, "Ignore the naysayers." is clutch. And other advice once one starts to rocket shoot like "Stay in your lane." is the absolute worst advice of all time. (IYKYK - Rest in peace Scott Adams)

Another thought - Einstein had reviewed thousands of patents when he worked on the train - that's a hell of data set for an LM to start with.