Hacker News Reader

Comment by rmnclmnt | Hacker News Reader

> It's funny how LLMs leak their test procedure docs into user-facing output.

You have to constantly fight so hard to not get this. And for the past few months it seems most people do not even care to remove it and have proper user facing docs

View on HN

> You have to constantly fight so hard to not get this.

By “fight so hard” you mean “do a bit of basic editing before publishing the text”?

You wouldn't have thrown a junior's text straight at end users without any review in the past (at least I hope not, though obviously some teams actually were and still are that lax), why do you expect to get away with skipping the review/edit step with your clockwork colleague?

Because we expect a junior colleague to learn from feedback and not have to fix the same problems in their output year after year.

But having learned from the feedback they or you then go off to work on something else and, unless you move onwards/upwards/both in perfect sync, and you end up with new juniors who need the feedback afresh.

Also: I've always avoided being anything like a lead or manager, but I do effectively have a couple of relative juniors ATM who I wish would have a better long-term learn/forget ratio when it comes to feedback from myself and elsewhere!

The people who don't care can output slop orders of magnitude faster than those that do.

And that's one the biggest issue right now unfortunately

Okay yes "fight so hard" might have been a bit stronger sorry for that. But it was more in line with "this has become so annoying recently" rightly so because yes you do need to remove the cruft that has nothing to be here and I don't remember being such as issue 6 months ago. The other part of it is to regularly remind colleagues of this rising issue because as I said, even experienced people tend not to care anymore, and this is saddening me.

And while in 2025 I considered AI coding agent in the realm of junior devs, we have been way way past that since early 2026 honestly.

I didn’t notice it when using Codex. Recently switched to Claude to test Opus 5.5, and it is constantly adding useless commentary.

I don’t think that’s specific to Claude though. I’ve seen people use GH Copilot harneds (don’t with which models) and it was even worst

Reply on news.ycombinator.com