It takes barely longer than that to do manually, the extra time really just being the typing out of the commit messages. Folks should have been doing this all along and it still shocks me to discover that they haven't been. However, I don't immediately dislike the idea of people using agents to do it, even though I'm sure it will occasionally introduce some strange choices and not fully capture the intention behind any given choice.
This whole thread reads like skill issues, sorry to say. This presumption that you have to stop work whilst you wait on a PR to be reviewed is absurd. Rebasing is not this impossible challenge and if it's stopping you making progress you need to grow up.
> you spend a LOT of time trying to get your PR reviewed.
I've fixed this issue in several teams I've joined. Maybe some people won't understand this, as I didn't until I observed it multiple times over.
There are teams out there, perhaps the majority, that simply leave the decision as to when a PR will be reviewed nebulous, and at the discretion of team members. There is no formal obligation to do them in a timely manner, and there are no consequences if they are not done.
The solve to this is obvious and easy:
- Automatically assign specific people to PRs. No general team assignment. The submitter can add specific people in addition to PR's if they need domain experts, but the normal case is random assignment.
- Require PR's to be done within 24 working hours. If you cannot do this for whatever reason, you must communicate this to the team.
- There are consequences if you violate this policy.
The last one is the hard part for cowardly teams and cowardly managers. You do have to stay on top of it initially, and even when people have accepted this and gotten used to it, you can't forget about it because people will drift.
This isn't to say I'm against the direct integration model you propose, I can also see the appeal, it's just that problems with PR flows are mostly about cowardly management, not anything much to do with the actual process.
At a previous job, it was the on-call engineer's duty to review PRs, as one of their responsibilities. A PR is just another interrupt, right?
We also paired this with giving the on call engineer near total freedom with what to do during their shifts, similar to 20% time (which was about the same percentage; 5 team members, weekly on call rotations.) They chose which tickets to pick up from the backlog, which also helped keep up with maintenance and taking care of bugs and issues that otherwise wouldn't get prioritized.
Used to be people sold capitalism as something that gave freedom to individuals. Now it's just the thing that forces us to to act against what we believe is best for ourselves and society at large. Anyone who expresses distaste for that is of course, out to lunch.
I'm not selling capitalism. I'm telling you that society is indifferent to your desire to program in the old ways, we're not going to start a worker's revolution for the sake of programmers who don't like coding agents. You can either adapt, or get left behind.
See my comment above - you still see AI as a tool because you're only considering what I call "AI" instead of aAI (actual AI).
Imagine Stephen Hawking level genius at every area of expertise, able to think faster than any human and cheaper than minimum wage but unable to interact with the physical world.
That's not a tool you adapt to use, that's a tool the owners of your company replace everyone with, except ironically those roughly minimum wage manual workers.
Absurd take. The response was completely measured, and even if it wasn't The Document Foundation has no obligation either legal or moral to present as professional. They are not a business.
You're missing the point, and also demonstrating it. This blog isn't about personal experience, and it makes no claims about LLM capability at all. It is simply about whether code, in either volume or quality, should be used as a proof claim.
> LLMs entice us with code too quickly. We are easily led.
Arguably _is_ your argument. That people aren't doing the above and it's causing problems. You probably agree that just spinning up Claude code on the regular plan without doing the above can still generate a fuck-ton of code but that shouldn't be used as evidence either for or against AI effectiveness.
reply