[Jimmc414]

Fight fire with fire. Ask Fable to conduct an adversarial /ultareview of their PR and send the same wall of text back to them. If there are excessive defects, ask them in standup if they actually reviewed the PR themselves before sending it. If there aren’t maybe they are on to something. I think like in law, the human submitting the work is responsible for its quality, not the AI.

[LambdaComplex]

> Ask Fable to conduct an adversarial /ultareview of their PR and send the same wall of text back to them.

This won't help. Your wall of text will just get fed right back into the LLM.

[Jensson]

It will help if your wall of text cost less tokens than theirs, they will run out before you do if you have the same company quota per person.

[Telemakhos]

I'm not sure what the right vocabulary would be to describe this, but this sounds more like the calculations behind nuclear war than a healthy collegiality or cooperative work relationship. This sets up a competition to determine a loser based on resource scarcity, not a way to achieve mutual goals to advance the organization's goals.

[mysterydip]

What I don’t understand is what value is the person adding to this equation? Put another way, what’s the difference between them feeding the wall of text to the LLM, and you feeding the wall of text to the LLM, bypassing them in the process entirely?

[Jimmc414]

The role of the person in the equation is to take personal responsibility for the proposed change and review the changes prior to PR submission. You can't put AI on a PIP. It's acceptable to use AI as a coding assistant in 2026, but if a human is not reviewing what they submit and taking responsibility, their value is on par with a ChatGPT subscription.

[loeg]

It helps in that it offloads the code review burden you'd otherwise be doing.

[rvz]

As a last resort, do the code-review with a live pair programming session.

If they can't explain their own code then it is by default a bad pull request.

At the end of the day, everyone's time is being wasted on tokens and on the increasing cognitive complexity of AI generated code.

[xgulfie]

So if they say "idk Claude did it", what would you write in the PR review box?

[Geezus_42]

REJECTED: Engineer does not understand what they wrote.

[CursedSilicon]

A teammate that can't write (or at least, can't explain) "their own code"

Actively drags down the morale and productivity of their team (because everyone is getting flooded with AI slop PR's)

AND costs far too much money relative to everyone else doing actual work? (token usage)

By god they sound like management material

[emodendroket]

I mean frankly this should just be part of the standard process. By the time any person is looking at it there's no reason it should not have gone through an AI review.