We need more infra in the cloud instead of focusing on local RTX cards.

We need OpenRunPods to run thick open weights models.

Build in the cloud rather than bet on "at the edge" being a Renaissance.

> No, but if I asked an intern to eat it for me, I wouldn't feel like I did anything at all.

That's a poor analogy.

If I asked an intern to implement a function, I know I did the instruction and that I worked through them. The intern did work, but I did fancy high level work and killed several birds with one stone.

Even better analogy: if I'm a film director, I'm working through a lot of people. The DP, the cast, the crew, the AD (though they're my boss, telling me what I can/can't budget for)...

The best analogy for AI is the "film director" analogy.

There are good directors and bad directors, good films and bad films. No director works alone (unless it's some kind of avant-garde film school project).

You wouldn't say a film director isn't doing work. That they can't be uniquely felt through their work. That what they're doing isn't hard, doesn't require talent/taste, and doesn't get better over time.

We're all basically becoming film directors.