Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by forestry | Hacker News Reader

Full thread

forestry·

Peer review of changes is still important.

View on HN

Multi-model cross-review is important

It's not actually, thats just shoving more shit into the shit pipeline.

Humans need to review this stuff yall there's no way around that, apparently to some, very inconvenient reality.

It’s clear that they want this to be true so bad that they’re just not going to do it, and will spend a ton of money on quality gates and mitigation strategies instead of just reading some code.

I'm all for using a council of LLMs, I wrote a tool for it https://github.com/joelio/owl - but you still need to read through PRs yourself, at the very least.

You can't rely on people spotting the significance of such changes

Absolutely.

Nothing in the PR jumps out as a red flag. Unless you know how the internals work, I suppose.

> Nothing in the PR jumps out as a red flag.

Made by AI?

Are you kidding? It's a very obvious case of quote injection. Not some subtle race condition or anything.

I think it's obvious too. I'd call out any case of `${{ }}` interpolation in a `run` block, and it's something I watch for in PRs. I also know other people don't watch for this, as I've corrected it about a hundred times. Over the last 10 years my average colleague understands less and less about injection or to watch for it at layer boundaries.

Shouldn't anyone reviewing such a PR know how the internals work?

Not anymore, it seems

Tests would have caught it = https://github.com/rhysd/actionlint injection check

also been a huge fan of zizmor (https://github.com/zizmorcore/zizmor) lately, basically: "am I going to footgun myself?"

I have been talking to people who want to autoreview and autoapprove "minor" AI prs. For security especially, I think if the models weren't enough to prevent the issues, they aren't enough to judge what is minor.

Reply on news.ycombinator.com