This project falls into the classic "More" trap. Agents are fast at creating code so let's make them even faster (more). However any rational observer can see that the bottlenecks for throughput are no longer at this segment of the process.

Human decision-making, communications and awareness are the key bottlenecks, not code generation and commit speed, by several orders of magnitude.

And I think that's a good thing if we want to avoid mass-psychosis.

Do you think it's possible in the next few years or so that agents will improve to the point that some of approval work can be offloaded to them?