And, lest you think generating "600,000 lines of production code in 60 days" [2] is potentially problematic, has also fully solved the primary failure modes of AI coding identified by Andrej Karpathy, once and for all: "Karpathy's four failure modes? Already covered." [1]

As someone who has experienced mania, including with a programming bent specifically, it's hard not to raise an eyebrow at the idiosyncratic human-y bits of his thinking floating up from the sea of em-dashes and it's not X it's Y in his manifestos.

Plus volunteering this [3] in an interview:

“I sleep, like, four hours a night right now,” he told his interviewer, fellow VC Bill Gurley, during an onstage interview Saturday. “I have cyber psychosis, but I think a third of the CEOs that I know have it as well,” he joked about his current AI obsession. (Tan’s assistant confirmed to us that he was joking. ...)

It’s like I was able to re-create my startup that took $10 million in VC capital and 10 people, and I worked on that for two years, and I took anti-narcoleptics — I remember, you know, sort of being on modafinil...

[1] https://github.com/garrytan/gstack

[2] https://github.com/garrytan/gstack/blob/main/docs/ON_THE_LOC...

[3] https://techcrunch.com/2026/03/17/why-garry-tans-claude-code...

Seeing a vulnerable set of kids happily playing and hearing a confident voice say "A shooter could end all this. We can prevent it" validates that and closes the sale.

If a cautious pragmatist goes to the demo thinking "i know crime stats have declined for decades and im concerned about misuse of technology." Then a performatively confident person says "this is a component of a massive surveillance state ripe for misuse. It will give us footage of crimes and only stop a small percentage of them," how well do you think it would sell?