80% of the code?! That's amazing. So. Amazing! I love the focus on the planning part and doing that well maximizes the chance of success for the "one shot". And the fact he automated himself "out" of code reviews is also something to highlight for a lot of folks who are still struggling to understand the real gains.
I mean, imagine a life with LESS code reviews. It's a dream!
And the focus on prototypes, all the things, is especially refreshing. I can't stand reading a 10-page PRD anymore and want to roll my eyes while I start drooling with boredom. No, just show me the goods. Show me what you were thinking! You can do that now. Right? Yes.
Yes. This is definitely the year for the ADHD. We've always been here. But perhaps the technology has finally caught up to us. About fucking time.
I'm writing my own MCP connectors. It's really helping me. Now I'm building a sort of AI system in a free virtual machine with a ton of resources at my disposal.
Does Boris share or write about his work back in Meta on code quality? I would really love to know more and learn from his experience.
> One of the ideas was a centralized way to prioritize the different kind of code quality efforts. The second thing was figuring out the impact of code quality on engineering productivity, which turned out to be significant. How did you measure? What did you find there? There was a bunch of stuff. I think some of this has been published.
He mentioned it was published :D Anything that's more tactical rather than purely strategic is what I'm hoping for.
80% of the code?! That's amazing. So. Amazing! I love the focus on the planning part and doing that well maximizes the chance of success for the "one shot". And the fact he automated himself "out" of code reviews is also something to highlight for a lot of folks who are still struggling to understand the real gains.
I mean, imagine a life with LESS code reviews. It's a dream!
And the focus on prototypes, all the things, is especially refreshing. I can't stand reading a 10-page PRD anymore and want to roll my eyes while I start drooling with boredom. No, just show me the goods. Show me what you were thinking! You can do that now. Right? Yes.
Yes. This is definitely the year for the ADHD. We've always been here. But perhaps the technology has finally caught up to us. About fucking time.
I just finished listening the pod between Boris and Lenny. :D
Will listen to this one next. I bet you guys have different angles.
I'm writing my own MCP connectors. It's really helping me. Now I'm building a sort of AI system in a free virtual machine with a ton of resources at my disposal.
Does Boris share or write about his work back in Meta on code quality? I would really love to know more and learn from his experience.
> One of the ideas was a centralized way to prioritize the different kind of code quality efforts. The second thing was figuring out the impact of code quality on engineering productivity, which turned out to be significant. How did you measure? What did you find there? There was a bunch of stuff. I think some of this has been published.
He mentioned it was published :D Anything that's more tactical rather than purely strategic is what I'm hoping for.