[blutoot]

Since the cat is out of the bag (i.e. there's no stopping of LLM-generated code / PR / issues now that vibe-coding is fairly universally accessible), the only thing in our (especially those who are custodians of software systems and products) control is to invest a lot more in testing and evals. Just plain opposing LLM-generated content as a policy is a losing battle at this point..

[rester324]

> to invest a lot more in testing and evals

I don't think this will work. The same arguments could have been said to mitigate junior devs' work or short timeline/high stakes project technical debt and rarely ever anyone listened

[AlecSchueler]

Because there were other solutions at that time, but now the situation is materially different. I think we're already seeing a lot more test driven development as well as documentation of style norms that were necessitated by things like agents.md but whicj would have been useful ten years ago too, and it's still very early days

[catlifeonmars]

I disagree. I think there’s a near future where this is true, but we’re still at the point where you can cut down on a lot of spam/slop by rejecting the class of LLM-generated content as a policy.