I haven't opened my IDE in months. I only skim the MRs to make sure there are no glaring issues.
Success is a good set of skills, a good up front design for your feature, architecture docs in your repo, lots of automated linting, unit testing, AI MR reviews, and black box e2e testing.
I doubt I'll ever _have_ to write a line of code again.
All of my time is spent juggling 5-20 agents, mostly planning and responding to the agents escalations.
GPT 6 Sol / GPT 6 Luna are my bread and butter and spec-driven design works great.
Like 75% of the small issues that used to take me a few hours or half a day in 2021 take me like 15 minutes to ship now start to finish, and I can ship them while doing other things.
I can also ship slop if the stakes are 0. The code I write has stakes. Thousands of dollars per false positive, which happens to be approximately the entire margin that we’re operating within. If a false positive occurs and I can’t explain it because I shipped slop, then it’s curtains for me - and our contract.
What kind of coding are you using these models for? Most of the people I know who share your perspective never go beyond the prototyping stage. I’d be curious to hear from anyone who’s been AI coding for more than six months, shipping it to real users, and isn’t looking at their code at all.