Sam, in his typical ignorance, has it exactly backward. In the long-running argument between those who say scaling is enough for AGI and those who say we need new algorithms, transformers are a massive victory for the latter - they prove their point.
Sam Altman said the smartest scientists in AI are the ones who held the entire field back. The experts were the problem.
This is one of the most uncomfortable things he said all night.
Altman said the field was honestly held back by a generation of scientists who were too certain about what scaling would not produce. The people with the most credibility were the most wrong.
Then he explained why.
It was not about intelligence. It was about identity.
He said when you make your identity about a particular belief, that something will work or won't work, and then the data disproves you, you get stuck. You are too attached to the belief to let it go. You cannot see the truth anymore.
The smarter you are, the more confidently you defend the wrong position.
He pointed at the trolls who spent years saying scaling was a dead end, a fraud, a company destined to fail. The data kept proving them wrong. They kept repeating themselves anyway.
He called that a form of insanity.
Then he turned it around. He said it is a reminder in both directions. Including for the people who are currently right.
The lesson is not that experts are dumb.
It is that the moment a belief becomes who you are, it stops being something you can update.
(Watch the full talk on YouTube at Stanford Online channel)
