Hacker News Reader

… how are you getting actual usable output at that scale? I have to baby my AI in 1 minute increments or it just doesn’t arrive at the correct solution at all.

Using Codex 5.2

View on HN

Perhaps the prompts you are using could do with some love. We're pretty consistently getting great results up to and beyond the 10 minute mark in a large monorepo.

We tend to use Opus 4.6 High and GPT 5.4 High.

I mean, why do you think people are burning out?

Due to prolonged stress, which lack of control is the main contributor e.g. you have expectations, you cannot control variable x,y,z, which leads to stress, which over long period of causes burn out.

In case it wasn’t obvious, I was being facetious. You can’t just let the AI rip without putting effort into constructing good input and verifying the output and expect anything good to happen, which is what the gp was asking.

There’s no secret into how people are getting “10x”, or at least claiming to, they’re just working more.

Reply on news.ycombinator.com