- cross-posted to:
- programming@lemmy.ml
- cross-posted to:
- programming@lemmy.ml
You must log in or # to comment.
I feel the Team Fabric point so strongly. My team has gone from 2 reviewers per PR, to now 1, and open conversations about going to 0 with only AI review.
Feels less like a team every day, and more like a room of individuals, with less and less understanding and insight into what others are doing. Everyone is carving out their own kingdoms in the repo, that only they and their agent understand and can operate on, with internal patterns and designs.
Do we not see how big a risk this is if anyone leaves? Code review was for finding issues for sure, but for me that is at most half the purpose. The other purpose is driving consistency across the codebase, and disseminating knowledge amongst the team.
I feel that despite the stereotype of software engineers as loners, a lot of people I’ve worked with are deeply collaborative, and this is fuel on the burnout fire.
It’s crazy how little we as coworkers ask each other for help now. It used to be nearly daily for my team, could last 2 minutes or 2 hours but it was always an interesting moment
My colleague who didn’t ask nor describe his changes now generates descriptions and code comments through AI and it doesn’t improve anything. It’s verbose, imprecise, confusing, and irritating.
I wonder if and how much communication reduced with my other colleagues. I guess probably a bit where they now ask AI (first). But not significantly, in my team, luckily. We still regularly talk. But maybe it’s on a path of reduction right now. I would find it sad and bad as well.
Oh yea I see what you’re talking about. Some of my colleagues used to do that, then we decided together to forbid it. If we review or reply to someone else’s code it’s as a human. Sure an Ai can have an automatic review pass, but the human pass stays human
And yet, the latest generation of models is surprisingly underwhelming.
Hard disagree. The latest generation (Astra 6/Opus 5.5) is the first one that doesn’t produce slop IMO. They basically fixed Claudish, the code quality (at least in Rust) is close to what I would write most of the time, they don’t spew a gazillion useless comments through the code, etc.
I don’t think you can talk about agentic coding without saying which models you’re talking about - there’s a huge difference between the latest frontier models and those from 6 months ago.
