Hacker News Reader

That’s why it’s probably a good idea to never stick to one model but kick off a fleet on the same tasks and in parallel and drive consensus.

At least, that’s what I’ve found to be useful by pitting claude/codex/etc against each other to keep them a bit more honest.

View on HN

Honestly, even a single adversarial reviewer agent, even of the same model, goes a very long way to catching and fixing this kind of thing too.

Some really smart people think you need more, because often you have to adjust the problem to get useful results.

https://www.coreauto.com/blog/when-ai-starts-writing-systems...

You can have a solution generator and an auditor, but then you will might find a very specific solution to the problem that does not solve the general use-case, so then you might have to adjust the constraints of the problem by for example adding more examples/targets to drive the solution generator to be more general.

Reply on news.ycombinator.com