The human-perceived RGB is image 1 and the Tesla AI photon count reconstruction is image 2.
This is why Tesla FSD can see so well at night or through extreme glare.
@NickGibbsIAG@Tesla They just have other priorities; its not like they are stupid.
We often wonder why others aren't going crazy over these innovations, but we need to understand people are different
@DaveShapi Been following you for a while—this feels more hype than signal.
Current models are already strong with good context + tooling.
Real gap = no true online learning. Until that’s solved, “step changes” ≈ strategy, not substance.
I was lying in a medical facility on a remote island in the South Indian Ocean, recently shipwrecked and rescued.
On the 2nd day, the French doctor rushed in:“Is the Prime Minister of India an important man?”
I thought it a silly question—until he added: “He is going to call you.”
I thought someone was pulling a fast one. But the PM did call. He recalled meeting me at his residence and asked after my health. Between hiccups, pain and burning in my chest, I told him his words gave me the courage to return to sea.
He later spoke about it in Mann Ki Baat.
It did not end there. A few days later, INS Satpura arrived. I was airlifted, and the Commanding Officer told me the PMO had been seeking updates every 15 minutes!
Wishing the Prime Minister Shri @narendramodi a very happy (belated) birthday!
@simonw Meta-prompting is wild. If models can reliably build a prompt hierarchy, what stops us—inductively—from converging on one “master prompt” that generalizes to everything?