News for hackers. Stuff that matters.

eivindmeyer

we built zeroshot.sh to let you mechanically enforce this flow (and any other topology), want to check it out? :)
why measure something you can just enforce with something like opcore which we have built? https://github.com/the-open-engine/opcore/
Re:Ask HN: How do you review code nowadays? on Monday October 19, 2026 @02:18PM (#50155910)
You can standardize your entire review flow across your team and have it match your QA requirements with zeroshot.sh - could be worth checking out. I am one of the maintainers.
Re:Ask HN: How to speed up code-reviews? on Monday October 19, 2026 @02:17PM (#50155892)
We are building zeroshot.sh to automate the entire implementation, review, and acceptance testing workflow as a customizable graph with adverserial cycles that you can define to match your QA requirements. Should be relevant to check out for people in this thread. MIT open-source.

We built it for ourselves and havent reviewed code since starting to use it.

Re:How the Claude Code team does code review on Monday October 19, 2026 @02:15PM (#50155871)
We had some nice results showing that this actually helps (it has been our intution for a long time, but nice to show it!)

https://theopenengine.com/blog/review-loop/

Re:How the Claude Code team does code review on Monday October 19, 2026 @02:14PM (#50155859)
We built zeroshot.sh to automate our entire review and testing workflow. We found that the only thing that really worked was adverserial review cycles and that they had to be mechanically enforced, not based on instructions in skills. Should be relevant for you to check out :)
You can automate this entire orchestration with zeroshot.sh, mentioning it since it is relevant here.
Re:Why Are Coding Agents So Dumb? on Thursday October 15, 2026 @08:10AM (#50102515)
We are also building a framework for mechanically enforced adverserial review cycles - think it could be relevant here so I am mentioning it: zeroshot.sh
Re:AI coding agents generate more code, but not more software on Wednesday October 14, 2026 @06:49AM (#50085534)
Agents are fully capable of doing reviews as reliably as senior developers. They just need to be independent and adverserial, and validates the things you actually care about in your QA.
Re:AI coding agents generate more code, but not more software on Wednesday October 14, 2026 @06:46AM (#50085507)
We havent done manual code review for months actually. It is not a problem if you have adverserial review loops that automate your QA and mechanically enforce the orchestration of them. That is basically what the zeroshot framework we are building is for.
Re:AI coding agents generate more code, but not more software on Wednesday October 14, 2026 @06:42AM (#50085463)
Classic test theatre behavior. You can catch this with an adverserial reviewer though. This type of antipattern is why we build zeroshot
Re:AI coding agents generate more code, but not more software on Wednesday October 14, 2026 @06:41AM (#50085453)
Classic assert true theatre lol
Re:AI coding agents generate more code, but not more software on Tuesday October 13, 2026 @05:31AM (#50068985)
You dont have to review the code, but someone does. If it is a well-tuned adverserial reviewers, that would be more than sufficient. We are building zeroshot to let you customize that as a fixed graph for your repo, feel free to check it out!