Comment by root_axis | Hacker News Reader

Top New Best Ask Show Jobs

Comment by root_axis | Hacker News Reader

Parent Full thread

We've repeatedly seen that these test-driven LLM rewrites consistently produce absolute garbage.

Got any specific examples? I believe you, I'd just like some concrete examples to show my coworkers.

Sure.

https://www.theregister.com/software/2026/02/13/anthropics-a...

https://pivot-to-ai.com/2026/01/27/cursor-lies-about-vibe-co...

Thanks!

Reply on news.ycombinator.com