Andrej Karpathy on the No Priors podcast:

To get the most out of the tools that have become available now, you have to remove yourself as the bottleneck. You can’t be there to prompt the next thing. You have to arrange things such that they’re completely autonomous. How can you maximise your token throughput and not be in the loop? That is the goal.

The name of the game now is to increase your leverage. I put in very few tokens, just once in a while, and a huge amount of stuff happens on my behalf.

I tweeted about auto-research, and people liked it, but they haven’t maybe worked through the implications. For me, auto-research is an example of those implications. I don’t want to be the researcher in the loop looking at results. I’m holding the system back. So the question is: how do I refactor all the abstractions so that I arrange it once and hit go?

The name of the game is: how can you get more agents running for longer periods of time without your involvement, doing stuff on your behalf? Auto-research is just: here’s an objective, here’s a metric, here’s the boundaries of what you can and cannot do. And go.